Add files using upload-large-folder tool
Browse files- LLM-TTS/checkpoints/finetune_llama_xcodec_jonathan/checkpoint-2984/special_tokens_map.json +16 -0
- LLM-TTS/checkpoints/finetune_llama_xcodec_jonathan/checkpoint-2984/trainer_state.json +446 -0
- LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/config.json +39 -0
- LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/generation_config.json +10 -0
- LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/model.safetensors.index.json +262 -0
- LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/trainer_state.json +447 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/config.json +35 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/generation_config.json +9 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/model.safetensors.index.json +261 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/special_tokens_map.json +19 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/tokenizer_config.json +0 -0
- LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/trainer_state.json +447 -0
- LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/README.md +202 -0
- LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/adapter_config.json +36 -0
- LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/special_tokens_map.json +19 -0
- LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/tokenizer_config.json +0 -0
- LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/trainer_state.json +447 -0
- LLM-TTS/data/instruction_v2_en_snac_part1/dataset_info.json +23 -0
- LLM-TTS/data/instruction_v2_en_snac_part1/state.json +13 -0
- LLM-TTS/data/instruction_v2_en_snac_part2/dataset_info.json +23 -0
LLM-TTS/checkpoints/finetune_llama_xcodec_jonathan/checkpoint-2984/special_tokens_map.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
+
}
|
LLM-TTS/checkpoints/finetune_llama_xcodec_jonathan/checkpoint-2984/trainer_state.json
ADDED
|
@@ -0,0 +1,446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2984,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01675603217158177,
|
| 13 |
+
"grad_norm": 14.0,
|
| 14 |
+
"learning_rate": 4.9162198391420914e-05,
|
| 15 |
+
"loss": 8.2204,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03351206434316354,
|
| 20 |
+
"grad_norm": 20.75,
|
| 21 |
+
"learning_rate": 4.8324396782841826e-05,
|
| 22 |
+
"loss": 7.3167,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05026809651474531,
|
| 27 |
+
"grad_norm": 13.6875,
|
| 28 |
+
"learning_rate": 4.748659517426274e-05,
|
| 29 |
+
"loss": 7.2011,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06702412868632708,
|
| 34 |
+
"grad_norm": 10.625,
|
| 35 |
+
"learning_rate": 4.664879356568364e-05,
|
| 36 |
+
"loss": 7.151,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08378016085790885,
|
| 41 |
+
"grad_norm": 12.625,
|
| 42 |
+
"learning_rate": 4.581099195710456e-05,
|
| 43 |
+
"loss": 7.0011,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10053619302949061,
|
| 48 |
+
"grad_norm": 11.6875,
|
| 49 |
+
"learning_rate": 4.497319034852547e-05,
|
| 50 |
+
"loss": 6.986,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11729222520107238,
|
| 55 |
+
"grad_norm": 15.25,
|
| 56 |
+
"learning_rate": 4.4135388739946385e-05,
|
| 57 |
+
"loss": 6.9655,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13404825737265416,
|
| 62 |
+
"grad_norm": 13.0625,
|
| 63 |
+
"learning_rate": 4.32975871313673e-05,
|
| 64 |
+
"loss": 6.8495,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15080428954423591,
|
| 69 |
+
"grad_norm": 23.875,
|
| 70 |
+
"learning_rate": 4.24597855227882e-05,
|
| 71 |
+
"loss": 6.8134,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1675603217158177,
|
| 76 |
+
"grad_norm": 18.625,
|
| 77 |
+
"learning_rate": 4.162198391420912e-05,
|
| 78 |
+
"loss": 6.8637,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18431635388739948,
|
| 83 |
+
"grad_norm": 10.5625,
|
| 84 |
+
"learning_rate": 4.078418230563003e-05,
|
| 85 |
+
"loss": 6.7278,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.20107238605898123,
|
| 90 |
+
"grad_norm": 13.4375,
|
| 91 |
+
"learning_rate": 3.994638069705094e-05,
|
| 92 |
+
"loss": 6.8005,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.217828418230563,
|
| 97 |
+
"grad_norm": 19.25,
|
| 98 |
+
"learning_rate": 3.9108579088471856e-05,
|
| 99 |
+
"loss": 6.6877,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23458445040214476,
|
| 104 |
+
"grad_norm": 10.1875,
|
| 105 |
+
"learning_rate": 3.827077747989276e-05,
|
| 106 |
+
"loss": 6.7266,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25134048257372654,
|
| 111 |
+
"grad_norm": 12.875,
|
| 112 |
+
"learning_rate": 3.743297587131367e-05,
|
| 113 |
+
"loss": 6.6747,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2680965147453083,
|
| 118 |
+
"grad_norm": 7.96875,
|
| 119 |
+
"learning_rate": 3.659517426273459e-05,
|
| 120 |
+
"loss": 6.6867,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2848525469168901,
|
| 125 |
+
"grad_norm": 9.3125,
|
| 126 |
+
"learning_rate": 3.5757372654155496e-05,
|
| 127 |
+
"loss": 6.6286,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.30160857908847183,
|
| 132 |
+
"grad_norm": 10.4375,
|
| 133 |
+
"learning_rate": 3.491957104557641e-05,
|
| 134 |
+
"loss": 6.6277,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3183646112600536,
|
| 139 |
+
"grad_norm": 8.25,
|
| 140 |
+
"learning_rate": 3.408176943699732e-05,
|
| 141 |
+
"loss": 6.6448,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3351206434316354,
|
| 146 |
+
"grad_norm": 12.625,
|
| 147 |
+
"learning_rate": 3.324396782841823e-05,
|
| 148 |
+
"loss": 6.5791,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35187667560321717,
|
| 153 |
+
"grad_norm": 14.3125,
|
| 154 |
+
"learning_rate": 3.240616621983914e-05,
|
| 155 |
+
"loss": 6.5204,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.36863270777479895,
|
| 160 |
+
"grad_norm": 11.0,
|
| 161 |
+
"learning_rate": 3.1568364611260055e-05,
|
| 162 |
+
"loss": 6.5058,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3853887399463807,
|
| 167 |
+
"grad_norm": 12.5625,
|
| 168 |
+
"learning_rate": 3.073056300268097e-05,
|
| 169 |
+
"loss": 6.5841,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.40214477211796246,
|
| 174 |
+
"grad_norm": 9.5,
|
| 175 |
+
"learning_rate": 2.9892761394101875e-05,
|
| 176 |
+
"loss": 6.5307,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.41890080428954424,
|
| 181 |
+
"grad_norm": 11.875,
|
| 182 |
+
"learning_rate": 2.905495978552279e-05,
|
| 183 |
+
"loss": 6.4767,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.435656836461126,
|
| 188 |
+
"grad_norm": 10.0,
|
| 189 |
+
"learning_rate": 2.8217158176943702e-05,
|
| 190 |
+
"loss": 6.4272,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4524128686327078,
|
| 195 |
+
"grad_norm": 7.96875,
|
| 196 |
+
"learning_rate": 2.737935656836461e-05,
|
| 197 |
+
"loss": 6.4575,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4691689008042895,
|
| 202 |
+
"grad_norm": 9.5,
|
| 203 |
+
"learning_rate": 2.6541554959785526e-05,
|
| 204 |
+
"loss": 6.4347,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4859249329758713,
|
| 209 |
+
"grad_norm": 11.75,
|
| 210 |
+
"learning_rate": 2.5703753351206434e-05,
|
| 211 |
+
"loss": 6.3921,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5026809651474531,
|
| 216 |
+
"grad_norm": 11.25,
|
| 217 |
+
"learning_rate": 2.4865951742627346e-05,
|
| 218 |
+
"loss": 6.3659,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5194369973190348,
|
| 223 |
+
"grad_norm": 23.0,
|
| 224 |
+
"learning_rate": 2.4028150134048258e-05,
|
| 225 |
+
"loss": 6.4124,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5361930294906166,
|
| 230 |
+
"grad_norm": 8.3125,
|
| 231 |
+
"learning_rate": 2.319034852546917e-05,
|
| 232 |
+
"loss": 6.3554,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5529490616621984,
|
| 237 |
+
"grad_norm": 8.3125,
|
| 238 |
+
"learning_rate": 2.235254691689008e-05,
|
| 239 |
+
"loss": 6.3185,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5697050938337802,
|
| 244 |
+
"grad_norm": 9.75,
|
| 245 |
+
"learning_rate": 2.1514745308310993e-05,
|
| 246 |
+
"loss": 6.3039,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5864611260053619,
|
| 251 |
+
"grad_norm": 12.375,
|
| 252 |
+
"learning_rate": 2.0676943699731905e-05,
|
| 253 |
+
"loss": 6.3433,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6032171581769437,
|
| 258 |
+
"grad_norm": 9.0,
|
| 259 |
+
"learning_rate": 1.9839142091152816e-05,
|
| 260 |
+
"loss": 6.3082,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6199731903485255,
|
| 265 |
+
"grad_norm": 11.3125,
|
| 266 |
+
"learning_rate": 1.9001340482573725e-05,
|
| 267 |
+
"loss": 6.3417,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6367292225201072,
|
| 272 |
+
"grad_norm": 11.9375,
|
| 273 |
+
"learning_rate": 1.816353887399464e-05,
|
| 274 |
+
"loss": 6.2751,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.653485254691689,
|
| 279 |
+
"grad_norm": 9.8125,
|
| 280 |
+
"learning_rate": 1.7325737265415552e-05,
|
| 281 |
+
"loss": 6.3402,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6702412868632708,
|
| 286 |
+
"grad_norm": 14.4375,
|
| 287 |
+
"learning_rate": 1.648793565683646e-05,
|
| 288 |
+
"loss": 6.304,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6869973190348525,
|
| 293 |
+
"grad_norm": 8.8125,
|
| 294 |
+
"learning_rate": 1.5650134048257372e-05,
|
| 295 |
+
"loss": 6.2805,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7037533512064343,
|
| 300 |
+
"grad_norm": 9.9375,
|
| 301 |
+
"learning_rate": 1.4812332439678284e-05,
|
| 302 |
+
"loss": 6.279,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7205093833780161,
|
| 307 |
+
"grad_norm": 14.0,
|
| 308 |
+
"learning_rate": 1.3974530831099197e-05,
|
| 309 |
+
"loss": 6.2855,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7372654155495979,
|
| 314 |
+
"grad_norm": 12.9375,
|
| 315 |
+
"learning_rate": 1.3136729222520109e-05,
|
| 316 |
+
"loss": 6.3459,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7540214477211796,
|
| 321 |
+
"grad_norm": 15.0625,
|
| 322 |
+
"learning_rate": 1.2298927613941019e-05,
|
| 323 |
+
"loss": 6.335,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7707774798927614,
|
| 328 |
+
"grad_norm": 9.3125,
|
| 329 |
+
"learning_rate": 1.1461126005361931e-05,
|
| 330 |
+
"loss": 6.3235,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7875335120643432,
|
| 335 |
+
"grad_norm": 12.5625,
|
| 336 |
+
"learning_rate": 1.0623324396782843e-05,
|
| 337 |
+
"loss": 6.2252,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8042895442359249,
|
| 342 |
+
"grad_norm": 7.5,
|
| 343 |
+
"learning_rate": 9.785522788203753e-06,
|
| 344 |
+
"loss": 6.3526,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8210455764075067,
|
| 349 |
+
"grad_norm": 12.9375,
|
| 350 |
+
"learning_rate": 8.947721179624666e-06,
|
| 351 |
+
"loss": 6.2832,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8378016085790885,
|
| 356 |
+
"grad_norm": 8.3125,
|
| 357 |
+
"learning_rate": 8.109919571045576e-06,
|
| 358 |
+
"loss": 6.3133,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8545576407506702,
|
| 363 |
+
"grad_norm": 11.375,
|
| 364 |
+
"learning_rate": 7.272117962466489e-06,
|
| 365 |
+
"loss": 6.3058,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.871313672922252,
|
| 370 |
+
"grad_norm": 10.3125,
|
| 371 |
+
"learning_rate": 6.4343163538874e-06,
|
| 372 |
+
"loss": 6.2172,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8880697050938338,
|
| 377 |
+
"grad_norm": 9.75,
|
| 378 |
+
"learning_rate": 5.596514745308312e-06,
|
| 379 |
+
"loss": 6.2444,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9048257372654156,
|
| 384 |
+
"grad_norm": 9.1875,
|
| 385 |
+
"learning_rate": 4.758713136729223e-06,
|
| 386 |
+
"loss": 6.2372,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9215817694369973,
|
| 391 |
+
"grad_norm": 13.3125,
|
| 392 |
+
"learning_rate": 3.920911528150134e-06,
|
| 393 |
+
"loss": 6.3095,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.938337801608579,
|
| 398 |
+
"grad_norm": 11.75,
|
| 399 |
+
"learning_rate": 3.0831099195710457e-06,
|
| 400 |
+
"loss": 6.2757,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9550938337801609,
|
| 405 |
+
"grad_norm": 9.3125,
|
| 406 |
+
"learning_rate": 2.2453083109919575e-06,
|
| 407 |
+
"loss": 6.2993,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9718498659517426,
|
| 412 |
+
"grad_norm": 9.3125,
|
| 413 |
+
"learning_rate": 1.4075067024128687e-06,
|
| 414 |
+
"loss": 6.2662,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9886058981233244,
|
| 419 |
+
"grad_norm": 25.625,
|
| 420 |
+
"learning_rate": 5.697050938337802e-07,
|
| 421 |
+
"loss": 6.2405,
|
| 422 |
+
"step": 2950
|
| 423 |
+
}
|
| 424 |
+
],
|
| 425 |
+
"logging_steps": 50,
|
| 426 |
+
"max_steps": 2984,
|
| 427 |
+
"num_input_tokens_seen": 0,
|
| 428 |
+
"num_train_epochs": 1,
|
| 429 |
+
"save_steps": 5000,
|
| 430 |
+
"stateful_callbacks": {
|
| 431 |
+
"TrainerControl": {
|
| 432 |
+
"args": {
|
| 433 |
+
"should_epoch_stop": false,
|
| 434 |
+
"should_evaluate": false,
|
| 435 |
+
"should_log": false,
|
| 436 |
+
"should_save": true,
|
| 437 |
+
"should_training_stop": true
|
| 438 |
+
},
|
| 439 |
+
"attributes": {}
|
| 440 |
+
}
|
| 441 |
+
},
|
| 442 |
+
"total_flos": 2.3213450259634176e+16,
|
| 443 |
+
"train_batch_size": 1,
|
| 444 |
+
"trial_name": null,
|
| 445 |
+
"trial_params": null
|
| 446 |
+
}
|
LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
128001,
|
| 10 |
+
128008,
|
| 11 |
+
128009
|
| 12 |
+
],
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 3072,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 8192,
|
| 18 |
+
"max_position_embeddings": 131072,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
+
"model_type": "llama",
|
| 21 |
+
"num_attention_heads": 24,
|
| 22 |
+
"num_hidden_layers": 28,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-05,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"factor": 32.0,
|
| 28 |
+
"high_freq_factor": 4.0,
|
| 29 |
+
"low_freq_factor": 1.0,
|
| 30 |
+
"original_max_position_embeddings": 8192,
|
| 31 |
+
"rope_type": "llama3"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 500000.0,
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"torch_dtype": "bfloat16",
|
| 36 |
+
"transformers_version": "4.53.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 193803
|
| 39 |
+
}
|
LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"transformers_version": "4.53.2"
|
| 10 |
+
}
|
LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3414110208,
|
| 4 |
+
"total_size": 6828220416
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 261 |
+
}
|
| 262 |
+
}
|
LLM-TTS/checkpoints/finetune_llama_xcodec_ronaldinho/checkpoint-2984/trainer_state.json
ADDED
|
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2984,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01675603217158177,
|
| 14 |
+
"grad_norm": 12.5,
|
| 15 |
+
"learning_rate": 4.9178954423592495e-05,
|
| 16 |
+
"loss": 8.4087,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03351206434316354,
|
| 21 |
+
"grad_norm": 22.5,
|
| 22 |
+
"learning_rate": 4.834115281501341e-05,
|
| 23 |
+
"loss": 7.4317,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05026809651474531,
|
| 28 |
+
"grad_norm": 13.25,
|
| 29 |
+
"learning_rate": 4.750335120643432e-05,
|
| 30 |
+
"loss": 7.2383,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06702412868632708,
|
| 35 |
+
"grad_norm": 9.75,
|
| 36 |
+
"learning_rate": 4.666554959785523e-05,
|
| 37 |
+
"loss": 7.1593,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08378016085790885,
|
| 42 |
+
"grad_norm": 12.3125,
|
| 43 |
+
"learning_rate": 4.582774798927614e-05,
|
| 44 |
+
"loss": 7.1069,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10053619302949061,
|
| 49 |
+
"grad_norm": 10.5625,
|
| 50 |
+
"learning_rate": 4.4989946380697054e-05,
|
| 51 |
+
"loss": 7.046,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11729222520107238,
|
| 56 |
+
"grad_norm": 12.75,
|
| 57 |
+
"learning_rate": 4.4152144772117966e-05,
|
| 58 |
+
"loss": 7.0548,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13404825737265416,
|
| 63 |
+
"grad_norm": 10.1875,
|
| 64 |
+
"learning_rate": 4.331434316353888e-05,
|
| 65 |
+
"loss": 6.934,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.15080428954423591,
|
| 70 |
+
"grad_norm": 20.0,
|
| 71 |
+
"learning_rate": 4.247654155495979e-05,
|
| 72 |
+
"loss": 6.8463,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1675603217158177,
|
| 77 |
+
"grad_norm": 18.625,
|
| 78 |
+
"learning_rate": 4.16387399463807e-05,
|
| 79 |
+
"loss": 6.887,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18431635388739948,
|
| 84 |
+
"grad_norm": 11.6875,
|
| 85 |
+
"learning_rate": 4.0800938337801606e-05,
|
| 86 |
+
"loss": 6.8541,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20107238605898123,
|
| 91 |
+
"grad_norm": 11.625,
|
| 92 |
+
"learning_rate": 3.9963136729222525e-05,
|
| 93 |
+
"loss": 6.7591,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.217828418230563,
|
| 98 |
+
"grad_norm": 17.25,
|
| 99 |
+
"learning_rate": 3.912533512064344e-05,
|
| 100 |
+
"loss": 6.7748,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.23458445040214476,
|
| 105 |
+
"grad_norm": 10.75,
|
| 106 |
+
"learning_rate": 3.828753351206434e-05,
|
| 107 |
+
"loss": 6.7847,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.25134048257372654,
|
| 112 |
+
"grad_norm": 13.3125,
|
| 113 |
+
"learning_rate": 3.744973190348526e-05,
|
| 114 |
+
"loss": 6.7546,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2680965147453083,
|
| 119 |
+
"grad_norm": 7.78125,
|
| 120 |
+
"learning_rate": 3.6611930294906165e-05,
|
| 121 |
+
"loss": 6.717,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2848525469168901,
|
| 126 |
+
"grad_norm": 8.375,
|
| 127 |
+
"learning_rate": 3.577412868632708e-05,
|
| 128 |
+
"loss": 6.6667,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.30160857908847183,
|
| 133 |
+
"grad_norm": 9.6875,
|
| 134 |
+
"learning_rate": 3.4936327077747996e-05,
|
| 135 |
+
"loss": 6.6401,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3183646112600536,
|
| 140 |
+
"grad_norm": 8.1875,
|
| 141 |
+
"learning_rate": 3.40985254691689e-05,
|
| 142 |
+
"loss": 6.6814,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3351206434316354,
|
| 147 |
+
"grad_norm": 12.1875,
|
| 148 |
+
"learning_rate": 3.326072386058981e-05,
|
| 149 |
+
"loss": 6.6621,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.35187667560321717,
|
| 154 |
+
"grad_norm": 11.1875,
|
| 155 |
+
"learning_rate": 3.2422922252010724e-05,
|
| 156 |
+
"loss": 6.5352,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.36863270777479895,
|
| 161 |
+
"grad_norm": 11.0625,
|
| 162 |
+
"learning_rate": 3.1585120643431636e-05,
|
| 163 |
+
"loss": 6.6053,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3853887399463807,
|
| 168 |
+
"grad_norm": 11.5625,
|
| 169 |
+
"learning_rate": 3.074731903485255e-05,
|
| 170 |
+
"loss": 6.5695,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.40214477211796246,
|
| 175 |
+
"grad_norm": 8.5625,
|
| 176 |
+
"learning_rate": 2.990951742627346e-05,
|
| 177 |
+
"loss": 6.5789,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.41890080428954424,
|
| 182 |
+
"grad_norm": 13.9375,
|
| 183 |
+
"learning_rate": 2.907171581769437e-05,
|
| 184 |
+
"loss": 6.4982,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.435656836461126,
|
| 189 |
+
"grad_norm": 9.5625,
|
| 190 |
+
"learning_rate": 2.823391420911528e-05,
|
| 191 |
+
"loss": 6.4928,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4524128686327078,
|
| 196 |
+
"grad_norm": 8.125,
|
| 197 |
+
"learning_rate": 2.7396112600536195e-05,
|
| 198 |
+
"loss": 6.517,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4691689008042895,
|
| 203 |
+
"grad_norm": 9.625,
|
| 204 |
+
"learning_rate": 2.6558310991957107e-05,
|
| 205 |
+
"loss": 6.4661,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4859249329758713,
|
| 210 |
+
"grad_norm": 12.1875,
|
| 211 |
+
"learning_rate": 2.5720509383378015e-05,
|
| 212 |
+
"loss": 6.4786,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5026809651474531,
|
| 217 |
+
"grad_norm": 11.0,
|
| 218 |
+
"learning_rate": 2.488270777479893e-05,
|
| 219 |
+
"loss": 6.4479,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5194369973190348,
|
| 224 |
+
"grad_norm": 22.875,
|
| 225 |
+
"learning_rate": 2.4044906166219842e-05,
|
| 226 |
+
"loss": 6.4969,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5361930294906166,
|
| 231 |
+
"grad_norm": 7.46875,
|
| 232 |
+
"learning_rate": 2.320710455764075e-05,
|
| 233 |
+
"loss": 6.3731,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5529490616621984,
|
| 238 |
+
"grad_norm": 8.5625,
|
| 239 |
+
"learning_rate": 2.2369302949061662e-05,
|
| 240 |
+
"loss": 6.4575,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5697050938337802,
|
| 245 |
+
"grad_norm": 9.0625,
|
| 246 |
+
"learning_rate": 2.1531501340482574e-05,
|
| 247 |
+
"loss": 6.3593,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5864611260053619,
|
| 252 |
+
"grad_norm": 13.3125,
|
| 253 |
+
"learning_rate": 2.069369973190349e-05,
|
| 254 |
+
"loss": 6.3739,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6032171581769437,
|
| 259 |
+
"grad_norm": 9.8125,
|
| 260 |
+
"learning_rate": 1.9855898123324398e-05,
|
| 261 |
+
"loss": 6.3837,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6199731903485255,
|
| 266 |
+
"grad_norm": 10.1875,
|
| 267 |
+
"learning_rate": 1.901809651474531e-05,
|
| 268 |
+
"loss": 6.4222,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6367292225201072,
|
| 273 |
+
"grad_norm": 11.875,
|
| 274 |
+
"learning_rate": 1.818029490616622e-05,
|
| 275 |
+
"loss": 6.343,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.653485254691689,
|
| 280 |
+
"grad_norm": 9.75,
|
| 281 |
+
"learning_rate": 1.7342493297587133e-05,
|
| 282 |
+
"loss": 6.3863,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6702412868632708,
|
| 287 |
+
"grad_norm": 14.1875,
|
| 288 |
+
"learning_rate": 1.6504691689008045e-05,
|
| 289 |
+
"loss": 6.355,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6869973190348525,
|
| 294 |
+
"grad_norm": 8.125,
|
| 295 |
+
"learning_rate": 1.5666890080428956e-05,
|
| 296 |
+
"loss": 6.3275,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7037533512064343,
|
| 301 |
+
"grad_norm": 8.9375,
|
| 302 |
+
"learning_rate": 1.4829088471849867e-05,
|
| 303 |
+
"loss": 6.3345,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7205093833780161,
|
| 308 |
+
"grad_norm": 13.875,
|
| 309 |
+
"learning_rate": 1.3991286863270778e-05,
|
| 310 |
+
"loss": 6.3538,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.7372654155495979,
|
| 315 |
+
"grad_norm": 14.3125,
|
| 316 |
+
"learning_rate": 1.3153485254691688e-05,
|
| 317 |
+
"loss": 6.3804,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7540214477211796,
|
| 322 |
+
"grad_norm": 14.125,
|
| 323 |
+
"learning_rate": 1.23156836461126e-05,
|
| 324 |
+
"loss": 6.3973,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7707774798927614,
|
| 329 |
+
"grad_norm": 9.25,
|
| 330 |
+
"learning_rate": 1.1477882037533512e-05,
|
| 331 |
+
"loss": 6.4097,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7875335120643432,
|
| 336 |
+
"grad_norm": 12.625,
|
| 337 |
+
"learning_rate": 1.0640080428954424e-05,
|
| 338 |
+
"loss": 6.318,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8042895442359249,
|
| 343 |
+
"grad_norm": 7.15625,
|
| 344 |
+
"learning_rate": 9.802278820375336e-06,
|
| 345 |
+
"loss": 6.4075,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8210455764075067,
|
| 350 |
+
"grad_norm": 11.8125,
|
| 351 |
+
"learning_rate": 8.964477211796247e-06,
|
| 352 |
+
"loss": 6.3107,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8378016085790885,
|
| 357 |
+
"grad_norm": 7.625,
|
| 358 |
+
"learning_rate": 8.126675603217159e-06,
|
| 359 |
+
"loss": 6.3745,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8545576407506702,
|
| 364 |
+
"grad_norm": 11.5625,
|
| 365 |
+
"learning_rate": 7.288873994638071e-06,
|
| 366 |
+
"loss": 6.3476,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.871313672922252,
|
| 371 |
+
"grad_norm": 11.0,
|
| 372 |
+
"learning_rate": 6.451072386058982e-06,
|
| 373 |
+
"loss": 6.3082,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8880697050938338,
|
| 378 |
+
"grad_norm": 10.8125,
|
| 379 |
+
"learning_rate": 5.613270777479894e-06,
|
| 380 |
+
"loss": 6.3253,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9048257372654156,
|
| 385 |
+
"grad_norm": 8.75,
|
| 386 |
+
"learning_rate": 4.7754691689008045e-06,
|
| 387 |
+
"loss": 6.288,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.9215817694369973,
|
| 392 |
+
"grad_norm": 12.6875,
|
| 393 |
+
"learning_rate": 3.9376675603217155e-06,
|
| 394 |
+
"loss": 6.3841,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.938337801608579,
|
| 399 |
+
"grad_norm": 11.25,
|
| 400 |
+
"learning_rate": 3.0998659517426277e-06,
|
| 401 |
+
"loss": 6.3819,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9550938337801609,
|
| 406 |
+
"grad_norm": 9.25,
|
| 407 |
+
"learning_rate": 2.262064343163539e-06,
|
| 408 |
+
"loss": 6.3775,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9718498659517426,
|
| 413 |
+
"grad_norm": 9.125,
|
| 414 |
+
"learning_rate": 1.4242627345844506e-06,
|
| 415 |
+
"loss": 6.3869,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9886058981233244,
|
| 420 |
+
"grad_norm": 26.125,
|
| 421 |
+
"learning_rate": 5.86461126005362e-07,
|
| 422 |
+
"loss": 6.2575,
|
| 423 |
+
"step": 2950
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"logging_steps": 50,
|
| 427 |
+
"max_steps": 2984,
|
| 428 |
+
"num_input_tokens_seen": 0,
|
| 429 |
+
"num_train_epochs": 1,
|
| 430 |
+
"save_steps": 5000,
|
| 431 |
+
"stateful_callbacks": {
|
| 432 |
+
"TrainerControl": {
|
| 433 |
+
"args": {
|
| 434 |
+
"should_epoch_stop": false,
|
| 435 |
+
"should_evaluate": false,
|
| 436 |
+
"should_log": false,
|
| 437 |
+
"should_save": true,
|
| 438 |
+
"should_training_stop": true
|
| 439 |
+
},
|
| 440 |
+
"attributes": {}
|
| 441 |
+
}
|
| 442 |
+
},
|
| 443 |
+
"total_flos": 2.3213450259634176e+16,
|
| 444 |
+
"train_batch_size": 1,
|
| 445 |
+
"trial_name": null,
|
| 446 |
+
"trial_params": null
|
| 447 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": 128001,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 3072,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 24,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": {
|
| 23 |
+
"factor": 32.0,
|
| 24 |
+
"high_freq_factor": 4.0,
|
| 25 |
+
"low_freq_factor": 1.0,
|
| 26 |
+
"original_max_position_embeddings": 8192,
|
| 27 |
+
"rope_type": "llama3"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 500000.0,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.51.3",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 156940
|
| 35 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "4.51.3"
|
| 9 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6601734144
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 260 |
+
}
|
| 261 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|audio|>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": {
|
| 6 |
+
"content": "<|begin_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"content": "<|eot_id|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
}
|
| 19 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
LLM-TTS/checkpoints/jonathan_finetune/checkpoint-2984/trainer_state.json
ADDED
|
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2984,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01675603217158177,
|
| 14 |
+
"grad_norm": 3.53125,
|
| 15 |
+
"learning_rate": 4.9178954423592495e-05,
|
| 16 |
+
"loss": 4.2472,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03351206434316354,
|
| 21 |
+
"grad_norm": 6.53125,
|
| 22 |
+
"learning_rate": 4.834115281501341e-05,
|
| 23 |
+
"loss": 4.0273,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05026809651474531,
|
| 28 |
+
"grad_norm": 3.4375,
|
| 29 |
+
"learning_rate": 4.750335120643432e-05,
|
| 30 |
+
"loss": 4.039,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06702412868632708,
|
| 35 |
+
"grad_norm": 2.25,
|
| 36 |
+
"learning_rate": 4.666554959785523e-05,
|
| 37 |
+
"loss": 3.9948,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08378016085790885,
|
| 42 |
+
"grad_norm": 3.34375,
|
| 43 |
+
"learning_rate": 4.582774798927614e-05,
|
| 44 |
+
"loss": 3.9269,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10053619302949061,
|
| 49 |
+
"grad_norm": 3.546875,
|
| 50 |
+
"learning_rate": 4.4989946380697054e-05,
|
| 51 |
+
"loss": 3.9419,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11729222520107238,
|
| 56 |
+
"grad_norm": 2.875,
|
| 57 |
+
"learning_rate": 4.4152144772117966e-05,
|
| 58 |
+
"loss": 3.915,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13404825737265416,
|
| 63 |
+
"grad_norm": 2.734375,
|
| 64 |
+
"learning_rate": 4.331434316353888e-05,
|
| 65 |
+
"loss": 3.9188,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.15080428954423591,
|
| 70 |
+
"grad_norm": 6.9375,
|
| 71 |
+
"learning_rate": 4.247654155495979e-05,
|
| 72 |
+
"loss": 3.8512,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1675603217158177,
|
| 77 |
+
"grad_norm": 5.65625,
|
| 78 |
+
"learning_rate": 4.16387399463807e-05,
|
| 79 |
+
"loss": 3.9142,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18431635388739948,
|
| 84 |
+
"grad_norm": 2.75,
|
| 85 |
+
"learning_rate": 4.0800938337801606e-05,
|
| 86 |
+
"loss": 3.8583,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20107238605898123,
|
| 91 |
+
"grad_norm": 3.03125,
|
| 92 |
+
"learning_rate": 3.9963136729222525e-05,
|
| 93 |
+
"loss": 3.8955,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.217828418230563,
|
| 98 |
+
"grad_norm": 7.21875,
|
| 99 |
+
"learning_rate": 3.912533512064344e-05,
|
| 100 |
+
"loss": 3.8571,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.23458445040214476,
|
| 105 |
+
"grad_norm": 2.59375,
|
| 106 |
+
"learning_rate": 3.828753351206434e-05,
|
| 107 |
+
"loss": 3.9075,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.25134048257372654,
|
| 112 |
+
"grad_norm": 3.28125,
|
| 113 |
+
"learning_rate": 3.744973190348526e-05,
|
| 114 |
+
"loss": 3.8933,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2680965147453083,
|
| 119 |
+
"grad_norm": 2.046875,
|
| 120 |
+
"learning_rate": 3.6611930294906165e-05,
|
| 121 |
+
"loss": 3.8752,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2848525469168901,
|
| 126 |
+
"grad_norm": 2.359375,
|
| 127 |
+
"learning_rate": 3.577412868632708e-05,
|
| 128 |
+
"loss": 3.8662,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.30160857908847183,
|
| 133 |
+
"grad_norm": 2.8125,
|
| 134 |
+
"learning_rate": 3.4936327077747996e-05,
|
| 135 |
+
"loss": 3.912,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3183646112600536,
|
| 140 |
+
"grad_norm": 1.953125,
|
| 141 |
+
"learning_rate": 3.40985254691689e-05,
|
| 142 |
+
"loss": 3.9365,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3351206434316354,
|
| 147 |
+
"grad_norm": 3.4375,
|
| 148 |
+
"learning_rate": 3.326072386058981e-05,
|
| 149 |
+
"loss": 3.8791,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.35187667560321717,
|
| 154 |
+
"grad_norm": 3.390625,
|
| 155 |
+
"learning_rate": 3.2422922252010724e-05,
|
| 156 |
+
"loss": 3.8536,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.36863270777479895,
|
| 161 |
+
"grad_norm": 3.1875,
|
| 162 |
+
"learning_rate": 3.1585120643431636e-05,
|
| 163 |
+
"loss": 3.8585,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3853887399463807,
|
| 168 |
+
"grad_norm": 3.40625,
|
| 169 |
+
"learning_rate": 3.074731903485255e-05,
|
| 170 |
+
"loss": 3.9163,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.40214477211796246,
|
| 175 |
+
"grad_norm": 2.34375,
|
| 176 |
+
"learning_rate": 2.990951742627346e-05,
|
| 177 |
+
"loss": 3.8529,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.41890080428954424,
|
| 182 |
+
"grad_norm": 3.140625,
|
| 183 |
+
"learning_rate": 2.907171581769437e-05,
|
| 184 |
+
"loss": 3.86,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.435656836461126,
|
| 189 |
+
"grad_norm": 2.40625,
|
| 190 |
+
"learning_rate": 2.823391420911528e-05,
|
| 191 |
+
"loss": 3.8541,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4524128686327078,
|
| 196 |
+
"grad_norm": 2.03125,
|
| 197 |
+
"learning_rate": 2.7396112600536195e-05,
|
| 198 |
+
"loss": 3.8549,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4691689008042895,
|
| 203 |
+
"grad_norm": 2.671875,
|
| 204 |
+
"learning_rate": 2.6558310991957107e-05,
|
| 205 |
+
"loss": 3.884,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4859249329758713,
|
| 210 |
+
"grad_norm": 3.34375,
|
| 211 |
+
"learning_rate": 2.5720509383378015e-05,
|
| 212 |
+
"loss": 3.8677,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5026809651474531,
|
| 217 |
+
"grad_norm": 2.984375,
|
| 218 |
+
"learning_rate": 2.488270777479893e-05,
|
| 219 |
+
"loss": 3.7921,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5194369973190348,
|
| 224 |
+
"grad_norm": 7.0,
|
| 225 |
+
"learning_rate": 2.4044906166219842e-05,
|
| 226 |
+
"loss": 3.8765,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5361930294906166,
|
| 231 |
+
"grad_norm": 1.7421875,
|
| 232 |
+
"learning_rate": 2.320710455764075e-05,
|
| 233 |
+
"loss": 3.7936,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5529490616621984,
|
| 238 |
+
"grad_norm": 1.8984375,
|
| 239 |
+
"learning_rate": 2.2369302949061662e-05,
|
| 240 |
+
"loss": 3.8304,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5697050938337802,
|
| 245 |
+
"grad_norm": 2.421875,
|
| 246 |
+
"learning_rate": 2.1531501340482574e-05,
|
| 247 |
+
"loss": 3.7994,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5864611260053619,
|
| 252 |
+
"grad_norm": 3.234375,
|
| 253 |
+
"learning_rate": 2.069369973190349e-05,
|
| 254 |
+
"loss": 3.8363,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6032171581769437,
|
| 259 |
+
"grad_norm": 2.46875,
|
| 260 |
+
"learning_rate": 1.9855898123324398e-05,
|
| 261 |
+
"loss": 3.8377,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6199731903485255,
|
| 266 |
+
"grad_norm": 2.296875,
|
| 267 |
+
"learning_rate": 1.901809651474531e-05,
|
| 268 |
+
"loss": 3.86,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6367292225201072,
|
| 273 |
+
"grad_norm": 3.546875,
|
| 274 |
+
"learning_rate": 1.818029490616622e-05,
|
| 275 |
+
"loss": 3.8127,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.653485254691689,
|
| 280 |
+
"grad_norm": 2.578125,
|
| 281 |
+
"learning_rate": 1.7342493297587133e-05,
|
| 282 |
+
"loss": 3.8481,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6702412868632708,
|
| 287 |
+
"grad_norm": 4.40625,
|
| 288 |
+
"learning_rate": 1.6504691689008045e-05,
|
| 289 |
+
"loss": 3.8308,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6869973190348525,
|
| 294 |
+
"grad_norm": 1.8984375,
|
| 295 |
+
"learning_rate": 1.5666890080428956e-05,
|
| 296 |
+
"loss": 3.7686,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7037533512064343,
|
| 301 |
+
"grad_norm": 2.109375,
|
| 302 |
+
"learning_rate": 1.4829088471849867e-05,
|
| 303 |
+
"loss": 3.8635,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7205093833780161,
|
| 308 |
+
"grad_norm": 3.8125,
|
| 309 |
+
"learning_rate": 1.3991286863270778e-05,
|
| 310 |
+
"loss": 3.8338,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.7372654155495979,
|
| 315 |
+
"grad_norm": 2.640625,
|
| 316 |
+
"learning_rate": 1.3153485254691688e-05,
|
| 317 |
+
"loss": 3.8528,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7540214477211796,
|
| 322 |
+
"grad_norm": 3.03125,
|
| 323 |
+
"learning_rate": 1.23156836461126e-05,
|
| 324 |
+
"loss": 3.879,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7707774798927614,
|
| 329 |
+
"grad_norm": 2.453125,
|
| 330 |
+
"learning_rate": 1.1477882037533512e-05,
|
| 331 |
+
"loss": 3.8653,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7875335120643432,
|
| 336 |
+
"grad_norm": 3.359375,
|
| 337 |
+
"learning_rate": 1.0640080428954424e-05,
|
| 338 |
+
"loss": 3.7811,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8042895442359249,
|
| 343 |
+
"grad_norm": 1.8125,
|
| 344 |
+
"learning_rate": 9.802278820375336e-06,
|
| 345 |
+
"loss": 3.864,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8210455764075067,
|
| 350 |
+
"grad_norm": 3.015625,
|
| 351 |
+
"learning_rate": 8.964477211796247e-06,
|
| 352 |
+
"loss": 3.8341,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8378016085790885,
|
| 357 |
+
"grad_norm": 2.109375,
|
| 358 |
+
"learning_rate": 8.126675603217159e-06,
|
| 359 |
+
"loss": 3.8547,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8545576407506702,
|
| 364 |
+
"grad_norm": 3.765625,
|
| 365 |
+
"learning_rate": 7.288873994638071e-06,
|
| 366 |
+
"loss": 3.8611,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.871313672922252,
|
| 371 |
+
"grad_norm": 2.390625,
|
| 372 |
+
"learning_rate": 6.451072386058982e-06,
|
| 373 |
+
"loss": 3.7803,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8880697050938338,
|
| 378 |
+
"grad_norm": 2.609375,
|
| 379 |
+
"learning_rate": 5.613270777479894e-06,
|
| 380 |
+
"loss": 3.8047,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9048257372654156,
|
| 385 |
+
"grad_norm": 2.09375,
|
| 386 |
+
"learning_rate": 4.7754691689008045e-06,
|
| 387 |
+
"loss": 3.8275,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.9215817694369973,
|
| 392 |
+
"grad_norm": 3.59375,
|
| 393 |
+
"learning_rate": 3.9376675603217155e-06,
|
| 394 |
+
"loss": 3.8354,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.938337801608579,
|
| 399 |
+
"grad_norm": 2.90625,
|
| 400 |
+
"learning_rate": 3.0998659517426277e-06,
|
| 401 |
+
"loss": 3.8245,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9550938337801609,
|
| 406 |
+
"grad_norm": 2.375,
|
| 407 |
+
"learning_rate": 2.262064343163539e-06,
|
| 408 |
+
"loss": 3.8646,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9718498659517426,
|
| 413 |
+
"grad_norm": 2.15625,
|
| 414 |
+
"learning_rate": 1.4242627345844506e-06,
|
| 415 |
+
"loss": 3.8213,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9886058981233244,
|
| 420 |
+
"grad_norm": 7.625,
|
| 421 |
+
"learning_rate": 5.86461126005362e-07,
|
| 422 |
+
"loss": 3.7671,
|
| 423 |
+
"step": 2950
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"logging_steps": 50,
|
| 427 |
+
"max_steps": 2984,
|
| 428 |
+
"num_input_tokens_seen": 0,
|
| 429 |
+
"num_train_epochs": 1,
|
| 430 |
+
"save_steps": 5000,
|
| 431 |
+
"stateful_callbacks": {
|
| 432 |
+
"TrainerControl": {
|
| 433 |
+
"args": {
|
| 434 |
+
"should_epoch_stop": false,
|
| 435 |
+
"should_evaluate": false,
|
| 436 |
+
"should_log": false,
|
| 437 |
+
"should_save": true,
|
| 438 |
+
"should_training_stop": true
|
| 439 |
+
},
|
| 440 |
+
"attributes": {}
|
| 441 |
+
}
|
| 442 |
+
},
|
| 443 |
+
"total_flos": 3.509068212041933e+16,
|
| 444 |
+
"train_batch_size": 1,
|
| 445 |
+
"trial_name": null,
|
| 446 |
+
"trial_params": null
|
| 447 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: canopylabs/orpheus-3b-0.1-ft
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/adapter_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "canopylabs/orpheus-3b-0.1-ft",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 512,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 256,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj"
|
| 31 |
+
],
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"trainable_token_indices": null,
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_rslora": false
|
| 36 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|audio|>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": {
|
| 6 |
+
"content": "<|begin_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"content": "<|eot_id|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
}
|
| 19 |
+
}
|
LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
LLM-TTS/checkpoints/jonathan_finetune_lora/checkpoint-2984/trainer_state.json
ADDED
|
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2984,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01675603217158177,
|
| 14 |
+
"grad_norm": 0.894202470779419,
|
| 15 |
+
"learning_rate": 4.9178954423592495e-05,
|
| 16 |
+
"loss": 4.3685,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03351206434316354,
|
| 21 |
+
"grad_norm": 1.6760941743850708,
|
| 22 |
+
"learning_rate": 4.834115281501341e-05,
|
| 23 |
+
"loss": 4.0974,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05026809651474531,
|
| 28 |
+
"grad_norm": 1.315443992614746,
|
| 29 |
+
"learning_rate": 4.750335120643432e-05,
|
| 30 |
+
"loss": 4.1001,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06702412868632708,
|
| 35 |
+
"grad_norm": 0.5858052968978882,
|
| 36 |
+
"learning_rate": 4.666554959785523e-05,
|
| 37 |
+
"loss": 4.0566,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08378016085790885,
|
| 42 |
+
"grad_norm": 0.8846954703330994,
|
| 43 |
+
"learning_rate": 4.582774798927614e-05,
|
| 44 |
+
"loss": 3.9923,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10053619302949061,
|
| 49 |
+
"grad_norm": 0.9141067862510681,
|
| 50 |
+
"learning_rate": 4.4989946380697054e-05,
|
| 51 |
+
"loss": 3.9989,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11729222520107238,
|
| 56 |
+
"grad_norm": 0.7609996795654297,
|
| 57 |
+
"learning_rate": 4.4152144772117966e-05,
|
| 58 |
+
"loss": 3.9808,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13404825737265416,
|
| 63 |
+
"grad_norm": 0.69050532579422,
|
| 64 |
+
"learning_rate": 4.331434316353888e-05,
|
| 65 |
+
"loss": 3.9847,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.15080428954423591,
|
| 70 |
+
"grad_norm": 1.9871259927749634,
|
| 71 |
+
"learning_rate": 4.247654155495979e-05,
|
| 72 |
+
"loss": 3.9124,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1675603217158177,
|
| 77 |
+
"grad_norm": 1.402071475982666,
|
| 78 |
+
"learning_rate": 4.16387399463807e-05,
|
| 79 |
+
"loss": 3.9818,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18431635388739948,
|
| 84 |
+
"grad_norm": 0.6597046256065369,
|
| 85 |
+
"learning_rate": 4.0800938337801606e-05,
|
| 86 |
+
"loss": 3.9283,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20107238605898123,
|
| 91 |
+
"grad_norm": 0.7212884426116943,
|
| 92 |
+
"learning_rate": 3.9963136729222525e-05,
|
| 93 |
+
"loss": 3.9589,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.217828418230563,
|
| 98 |
+
"grad_norm": 1.6944984197616577,
|
| 99 |
+
"learning_rate": 3.912533512064344e-05,
|
| 100 |
+
"loss": 3.9206,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.23458445040214476,
|
| 105 |
+
"grad_norm": 0.6426927447319031,
|
| 106 |
+
"learning_rate": 3.828753351206434e-05,
|
| 107 |
+
"loss": 3.9742,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.25134048257372654,
|
| 112 |
+
"grad_norm": 0.831523597240448,
|
| 113 |
+
"learning_rate": 3.744973190348526e-05,
|
| 114 |
+
"loss": 3.9554,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2680965147453083,
|
| 119 |
+
"grad_norm": 0.4929649531841278,
|
| 120 |
+
"learning_rate": 3.6611930294906165e-05,
|
| 121 |
+
"loss": 3.9391,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2848525469168901,
|
| 126 |
+
"grad_norm": 0.5525246262550354,
|
| 127 |
+
"learning_rate": 3.577412868632708e-05,
|
| 128 |
+
"loss": 3.9317,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.30160857908847183,
|
| 133 |
+
"grad_norm": 0.6773424744606018,
|
| 134 |
+
"learning_rate": 3.4936327077747996e-05,
|
| 135 |
+
"loss": 3.9766,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3183646112600536,
|
| 140 |
+
"grad_norm": 0.4641803801059723,
|
| 141 |
+
"learning_rate": 3.40985254691689e-05,
|
| 142 |
+
"loss": 4.0014,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3351206434316354,
|
| 147 |
+
"grad_norm": 0.7781908512115479,
|
| 148 |
+
"learning_rate": 3.326072386058981e-05,
|
| 149 |
+
"loss": 3.9436,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.35187667560321717,
|
| 154 |
+
"grad_norm": 0.8020728826522827,
|
| 155 |
+
"learning_rate": 3.2422922252010724e-05,
|
| 156 |
+
"loss": 3.9205,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.36863270777479895,
|
| 161 |
+
"grad_norm": 0.8074462413787842,
|
| 162 |
+
"learning_rate": 3.1585120643431636e-05,
|
| 163 |
+
"loss": 3.9309,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3853887399463807,
|
| 168 |
+
"grad_norm": 0.8561592102050781,
|
| 169 |
+
"learning_rate": 3.074731903485255e-05,
|
| 170 |
+
"loss": 3.9822,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.40214477211796246,
|
| 175 |
+
"grad_norm": 0.5495112538337708,
|
| 176 |
+
"learning_rate": 2.990951742627346e-05,
|
| 177 |
+
"loss": 3.9192,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.41890080428954424,
|
| 182 |
+
"grad_norm": 0.7179405093193054,
|
| 183 |
+
"learning_rate": 2.907171581769437e-05,
|
| 184 |
+
"loss": 3.9244,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.435656836461126,
|
| 189 |
+
"grad_norm": 0.6133170127868652,
|
| 190 |
+
"learning_rate": 2.823391420911528e-05,
|
| 191 |
+
"loss": 3.9198,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4524128686327078,
|
| 196 |
+
"grad_norm": 0.5052416920661926,
|
| 197 |
+
"learning_rate": 2.7396112600536195e-05,
|
| 198 |
+
"loss": 3.9216,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4691689008042895,
|
| 203 |
+
"grad_norm": 0.6917873620986938,
|
| 204 |
+
"learning_rate": 2.6558310991957107e-05,
|
| 205 |
+
"loss": 3.9526,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4859249329758713,
|
| 210 |
+
"grad_norm": 0.8156997561454773,
|
| 211 |
+
"learning_rate": 2.5720509383378015e-05,
|
| 212 |
+
"loss": 3.9341,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5026809651474531,
|
| 217 |
+
"grad_norm": 0.7477702498435974,
|
| 218 |
+
"learning_rate": 2.488270777479893e-05,
|
| 219 |
+
"loss": 3.8601,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5194369973190348,
|
| 224 |
+
"grad_norm": 1.652376651763916,
|
| 225 |
+
"learning_rate": 2.4044906166219842e-05,
|
| 226 |
+
"loss": 3.9369,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5361930294906166,
|
| 231 |
+
"grad_norm": 0.43560102581977844,
|
| 232 |
+
"learning_rate": 2.320710455764075e-05,
|
| 233 |
+
"loss": 3.8569,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5529490616621984,
|
| 238 |
+
"grad_norm": 0.4565785229206085,
|
| 239 |
+
"learning_rate": 2.2369302949061662e-05,
|
| 240 |
+
"loss": 3.8949,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5697050938337802,
|
| 245 |
+
"grad_norm": 0.5931048393249512,
|
| 246 |
+
"learning_rate": 2.1531501340482574e-05,
|
| 247 |
+
"loss": 3.8626,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5864611260053619,
|
| 252 |
+
"grad_norm": 0.8171066641807556,
|
| 253 |
+
"learning_rate": 2.069369973190349e-05,
|
| 254 |
+
"loss": 3.8973,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6032171581769437,
|
| 259 |
+
"grad_norm": 0.6017847061157227,
|
| 260 |
+
"learning_rate": 1.9855898123324398e-05,
|
| 261 |
+
"loss": 3.9021,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6199731903485255,
|
| 266 |
+
"grad_norm": 0.5669372081756592,
|
| 267 |
+
"learning_rate": 1.901809651474531e-05,
|
| 268 |
+
"loss": 3.9224,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6367292225201072,
|
| 273 |
+
"grad_norm": 0.8238586783409119,
|
| 274 |
+
"learning_rate": 1.818029490616622e-05,
|
| 275 |
+
"loss": 3.8753,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.653485254691689,
|
| 280 |
+
"grad_norm": 0.6140169501304626,
|
| 281 |
+
"learning_rate": 1.7342493297587133e-05,
|
| 282 |
+
"loss": 3.9085,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6702412868632708,
|
| 287 |
+
"grad_norm": 1.0417957305908203,
|
| 288 |
+
"learning_rate": 1.6504691689008045e-05,
|
| 289 |
+
"loss": 3.8859,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6869973190348525,
|
| 294 |
+
"grad_norm": 0.4688744843006134,
|
| 295 |
+
"learning_rate": 1.5666890080428956e-05,
|
| 296 |
+
"loss": 3.8291,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7037533512064343,
|
| 301 |
+
"grad_norm": 0.5231440663337708,
|
| 302 |
+
"learning_rate": 1.4829088471849867e-05,
|
| 303 |
+
"loss": 3.9273,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7205093833780161,
|
| 308 |
+
"grad_norm": 0.9120736122131348,
|
| 309 |
+
"learning_rate": 1.3991286863270778e-05,
|
| 310 |
+
"loss": 3.8895,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.7372654155495979,
|
| 315 |
+
"grad_norm": 0.6483898162841797,
|
| 316 |
+
"learning_rate": 1.3153485254691688e-05,
|
| 317 |
+
"loss": 3.9083,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7540214477211796,
|
| 322 |
+
"grad_norm": 0.7586402893066406,
|
| 323 |
+
"learning_rate": 1.23156836461126e-05,
|
| 324 |
+
"loss": 3.9381,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7707774798927614,
|
| 329 |
+
"grad_norm": 0.5775277614593506,
|
| 330 |
+
"learning_rate": 1.1477882037533512e-05,
|
| 331 |
+
"loss": 3.9181,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7875335120643432,
|
| 336 |
+
"grad_norm": 0.8397746086120605,
|
| 337 |
+
"learning_rate": 1.0640080428954424e-05,
|
| 338 |
+
"loss": 3.8338,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8042895442359249,
|
| 343 |
+
"grad_norm": 0.45658183097839355,
|
| 344 |
+
"learning_rate": 9.802278820375336e-06,
|
| 345 |
+
"loss": 3.9161,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8210455764075067,
|
| 350 |
+
"grad_norm": 0.770463764667511,
|
| 351 |
+
"learning_rate": 8.964477211796247e-06,
|
| 352 |
+
"loss": 3.8844,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8378016085790885,
|
| 357 |
+
"grad_norm": 0.5002725124359131,
|
| 358 |
+
"learning_rate": 8.126675603217159e-06,
|
| 359 |
+
"loss": 3.9072,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8545576407506702,
|
| 364 |
+
"grad_norm": 0.9032191038131714,
|
| 365 |
+
"learning_rate": 7.288873994638071e-06,
|
| 366 |
+
"loss": 3.9086,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.871313672922252,
|
| 371 |
+
"grad_norm": 0.6097182035446167,
|
| 372 |
+
"learning_rate": 6.451072386058982e-06,
|
| 373 |
+
"loss": 3.8329,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8880697050938338,
|
| 378 |
+
"grad_norm": 0.6825394630432129,
|
| 379 |
+
"learning_rate": 5.613270777479894e-06,
|
| 380 |
+
"loss": 3.8555,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9048257372654156,
|
| 385 |
+
"grad_norm": 0.5242748260498047,
|
| 386 |
+
"learning_rate": 4.7754691689008045e-06,
|
| 387 |
+
"loss": 3.8762,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.9215817694369973,
|
| 392 |
+
"grad_norm": 0.8877705335617065,
|
| 393 |
+
"learning_rate": 3.9376675603217155e-06,
|
| 394 |
+
"loss": 3.8787,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.938337801608579,
|
| 399 |
+
"grad_norm": 0.7941179871559143,
|
| 400 |
+
"learning_rate": 3.0998659517426277e-06,
|
| 401 |
+
"loss": 3.871,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9550938337801609,
|
| 406 |
+
"grad_norm": 0.599011242389679,
|
| 407 |
+
"learning_rate": 2.262064343163539e-06,
|
| 408 |
+
"loss": 3.9159,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9718498659517426,
|
| 413 |
+
"grad_norm": 0.5333606004714966,
|
| 414 |
+
"learning_rate": 1.4242627345844506e-06,
|
| 415 |
+
"loss": 3.8634,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9886058981233244,
|
| 420 |
+
"grad_norm": 1.6330139636993408,
|
| 421 |
+
"learning_rate": 5.86461126005362e-07,
|
| 422 |
+
"loss": 3.8142,
|
| 423 |
+
"step": 2950
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"logging_steps": 50,
|
| 427 |
+
"max_steps": 2984,
|
| 428 |
+
"num_input_tokens_seen": 0,
|
| 429 |
+
"num_train_epochs": 1,
|
| 430 |
+
"save_steps": 5000,
|
| 431 |
+
"stateful_callbacks": {
|
| 432 |
+
"TrainerControl": {
|
| 433 |
+
"args": {
|
| 434 |
+
"should_epoch_stop": false,
|
| 435 |
+
"should_evaluate": false,
|
| 436 |
+
"should_log": false,
|
| 437 |
+
"should_save": true,
|
| 438 |
+
"should_training_stop": true
|
| 439 |
+
},
|
| 440 |
+
"attributes": {}
|
| 441 |
+
}
|
| 442 |
+
},
|
| 443 |
+
"total_flos": 3.691820827900109e+16,
|
| 444 |
+
"train_batch_size": 1,
|
| 445 |
+
"trial_name": null,
|
| 446 |
+
"trial_params": null
|
| 447 |
+
}
|
LLM-TTS/data/instruction_v2_en_snac_part1/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"codes_list": {
|
| 6 |
+
"feature": {
|
| 7 |
+
"dtype": "int64",
|
| 8 |
+
"_type": "Value"
|
| 9 |
+
},
|
| 10 |
+
"_type": "Sequence"
|
| 11 |
+
},
|
| 12 |
+
"text": {
|
| 13 |
+
"dtype": "string",
|
| 14 |
+
"_type": "Value"
|
| 15 |
+
},
|
| 16 |
+
"act_instruction": {
|
| 17 |
+
"dtype": "string",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
LLM-TTS/data/instruction_v2_en_snac_part1/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "38ad352fb325c599",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
LLM-TTS/data/instruction_v2_en_snac_part2/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"codes_list": {
|
| 6 |
+
"feature": {
|
| 7 |
+
"dtype": "int64",
|
| 8 |
+
"_type": "Value"
|
| 9 |
+
},
|
| 10 |
+
"_type": "Sequence"
|
| 11 |
+
},
|
| 12 |
+
"text": {
|
| 13 |
+
"dtype": "string",
|
| 14 |
+
"_type": "Value"
|
| 15 |
+
},
|
| 16 |
+
"act_instruction": {
|
| 17 |
+
"dtype": "string",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|