NLU AI
commited on
commit first
Browse files- .gitattributes +1 -0
- config.json +32 -0
- generation_config.json +7 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +3 -0
- trainer_state.json +316 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloom-560m",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"masked_softmax_fusion": true,
|
| 17 |
+
"model_type": "bloom",
|
| 18 |
+
"n_head": 16,
|
| 19 |
+
"n_inner": null,
|
| 20 |
+
"n_layer": 24,
|
| 21 |
+
"offset_alibi": 100,
|
| 22 |
+
"pad_token_id": 3,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"skip_bias_add": true,
|
| 25 |
+
"skip_bias_add_qkv": false,
|
| 26 |
+
"slow_but_exact": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.27.1",
|
| 29 |
+
"unk_token_id": 0,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250880
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 3,
|
| 6 |
+
"transformers_version": "4.27.1"
|
| 7 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b5fa02ce1f2057ffdcccd86019817387a38e6b835bf0ecf5d2277b489b598e7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b61e78a8eb6d9cbd5a6a166fc6175a8fe2576db6e1178724577c1581b822de67
|
| 3 |
+
size 1064
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
|
| 3 |
+
size 14500438
|
trainer_state.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3440860215053765,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.9731182795698928e-05,
|
| 13 |
+
"loss": 9.7093,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 1.946236559139785e-05,
|
| 19 |
+
"loss": 0.7333,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 1.9193548387096777e-05,
|
| 25 |
+
"loss": 0.3919,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 1.89247311827957e-05,
|
| 31 |
+
"loss": 0.4332,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 1.8655913978494623e-05,
|
| 37 |
+
"loss": 0.4742,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"learning_rate": 1.838709677419355e-05,
|
| 43 |
+
"loss": 0.4272,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"learning_rate": 1.8118279569892473e-05,
|
| 49 |
+
"loss": 0.4382,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 1.78494623655914e-05,
|
| 55 |
+
"loss": 0.3068,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.24,
|
| 60 |
+
"learning_rate": 1.7580645161290325e-05,
|
| 61 |
+
"loss": 0.3431,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.27,
|
| 66 |
+
"learning_rate": 1.7311827956989248e-05,
|
| 67 |
+
"loss": 0.3652,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"learning_rate": 1.7043010752688175e-05,
|
| 73 |
+
"loss": 0.3845,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.32,
|
| 78 |
+
"learning_rate": 1.6774193548387098e-05,
|
| 79 |
+
"loss": 0.3613,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.35,
|
| 84 |
+
"learning_rate": 1.6505376344086024e-05,
|
| 85 |
+
"loss": 0.4529,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.38,
|
| 90 |
+
"learning_rate": 1.6236559139784947e-05,
|
| 91 |
+
"loss": 0.3652,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.4,
|
| 96 |
+
"learning_rate": 1.596774193548387e-05,
|
| 97 |
+
"loss": 0.3286,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.43,
|
| 102 |
+
"learning_rate": 1.5698924731182796e-05,
|
| 103 |
+
"loss": 0.4203,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.46,
|
| 108 |
+
"learning_rate": 1.5430107526881723e-05,
|
| 109 |
+
"loss": 0.347,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.48,
|
| 114 |
+
"learning_rate": 1.5161290322580646e-05,
|
| 115 |
+
"loss": 0.3657,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.51,
|
| 120 |
+
"learning_rate": 1.4892473118279572e-05,
|
| 121 |
+
"loss": 0.3914,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.54,
|
| 126 |
+
"learning_rate": 1.4623655913978497e-05,
|
| 127 |
+
"loss": 0.3301,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.56,
|
| 132 |
+
"learning_rate": 1.4354838709677421e-05,
|
| 133 |
+
"loss": 0.3266,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.59,
|
| 138 |
+
"learning_rate": 1.4086021505376346e-05,
|
| 139 |
+
"loss": 0.3893,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.62,
|
| 144 |
+
"learning_rate": 1.381720430107527e-05,
|
| 145 |
+
"loss": 0.331,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.65,
|
| 150 |
+
"learning_rate": 1.3548387096774194e-05,
|
| 151 |
+
"loss": 0.3853,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.67,
|
| 156 |
+
"learning_rate": 1.3279569892473118e-05,
|
| 157 |
+
"loss": 0.3697,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.7,
|
| 162 |
+
"learning_rate": 1.3010752688172043e-05,
|
| 163 |
+
"loss": 0.4314,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.73,
|
| 168 |
+
"learning_rate": 1.274193548387097e-05,
|
| 169 |
+
"loss": 0.3491,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 1.2473118279569894e-05,
|
| 175 |
+
"loss": 0.3355,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.78,
|
| 180 |
+
"learning_rate": 1.2204301075268819e-05,
|
| 181 |
+
"loss": 0.353,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.81,
|
| 186 |
+
"learning_rate": 1.1935483870967743e-05,
|
| 187 |
+
"loss": 0.3984,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.83,
|
| 192 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 193 |
+
"loss": 0.3151,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.86,
|
| 198 |
+
"learning_rate": 1.1397849462365593e-05,
|
| 199 |
+
"loss": 0.3339,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.89,
|
| 204 |
+
"learning_rate": 1.1129032258064516e-05,
|
| 205 |
+
"loss": 0.3183,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.91,
|
| 210 |
+
"learning_rate": 1.086021505376344e-05,
|
| 211 |
+
"loss": 0.3476,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.94,
|
| 216 |
+
"learning_rate": 1.0591397849462367e-05,
|
| 217 |
+
"loss": 0.4169,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.97,
|
| 222 |
+
"learning_rate": 1.0322580645161291e-05,
|
| 223 |
+
"loss": 0.3493,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.99,
|
| 228 |
+
"learning_rate": 1.0053763440860216e-05,
|
| 229 |
+
"loss": 0.3481,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.02,
|
| 234 |
+
"learning_rate": 9.78494623655914e-06,
|
| 235 |
+
"loss": 0.2469,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.05,
|
| 240 |
+
"learning_rate": 9.516129032258065e-06,
|
| 241 |
+
"loss": 0.2227,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.08,
|
| 246 |
+
"learning_rate": 9.24731182795699e-06,
|
| 247 |
+
"loss": 0.232,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.1,
|
| 252 |
+
"learning_rate": 8.978494623655915e-06,
|
| 253 |
+
"loss": 0.1878,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.13,
|
| 258 |
+
"learning_rate": 8.70967741935484e-06,
|
| 259 |
+
"loss": 0.2655,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.16,
|
| 264 |
+
"learning_rate": 8.440860215053764e-06,
|
| 265 |
+
"loss": 0.1786,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.18,
|
| 270 |
+
"learning_rate": 8.172043010752689e-06,
|
| 271 |
+
"loss": 0.1902,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.21,
|
| 276 |
+
"learning_rate": 7.903225806451613e-06,
|
| 277 |
+
"loss": 0.227,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.24,
|
| 282 |
+
"learning_rate": 7.634408602150538e-06,
|
| 283 |
+
"loss": 0.2045,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.26,
|
| 288 |
+
"learning_rate": 7.365591397849463e-06,
|
| 289 |
+
"loss": 0.2533,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.29,
|
| 294 |
+
"learning_rate": 7.096774193548388e-06,
|
| 295 |
+
"loss": 0.1642,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.32,
|
| 300 |
+
"learning_rate": 6.827956989247312e-06,
|
| 301 |
+
"loss": 0.1756,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.34,
|
| 306 |
+
"learning_rate": 6.5591397849462365e-06,
|
| 307 |
+
"loss": 0.1804,
|
| 308 |
+
"step": 500
|
| 309 |
+
}
|
| 310 |
+
],
|
| 311 |
+
"max_steps": 744,
|
| 312 |
+
"num_train_epochs": 2,
|
| 313 |
+
"total_flos": 928706985984000.0,
|
| 314 |
+
"trial_name": null,
|
| 315 |
+
"trial_params": null
|
| 316 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf2e583b8932299d24097286059a262f1f217cb71ee569ecd1f4587b206a4deb
|
| 3 |
+
size 3960
|