Commit
•
9a7feee
1
Parent(s):
7cc9873
Upload with huggingface_hub
Browse files- checkpoint-4100/config.json +28 -0
- checkpoint-4100/optimizer.pt +3 -0
- checkpoint-4100/pytorch_model.bin +3 -0
- checkpoint-4100/rng_state.pth +3 -0
- checkpoint-4100/scaler.pt +3 -0
- checkpoint-4100/scheduler.pt +3 -0
- checkpoint-4100/trainer_state.json +262 -0
- checkpoint-4100/training_args.bin +3 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-4100/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 260,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 3,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"sep_token_id": 2,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.27.0.dev0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-4100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c43d112443fe0bb38ffc7bb1c8684a0d191ad5eca208dcc6a96f6018e58b0199
|
| 3 |
+
size 883771077
|
checkpoint-4100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67ef1b00f43e7cabaf9575eaca740be0e0fb5f547b43f195aec4cf5dc584236d
|
| 3 |
+
size 441897977
|
checkpoint-4100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b79e65557cacef6aef384f792bcf9f17c1c25c260b360cb523012dc23e8950d
|
| 3 |
+
size 14511
|
checkpoint-4100/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26427c96ce120e337ff0677c51ab5817336f7be11273621e07618d7e9dcd9d80
|
| 3 |
+
size 557
|
checkpoint-4100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5453d756e7892a71b01e46c6c111f4dce2930b27dcbd01cfa12939ba4e60e2d0
|
| 3 |
+
size 627
|
checkpoint-4100/trainer_state.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 32.03103782735209,
|
| 5 |
+
"global_step": 4100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.78,
|
| 12 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 13 |
+
"loss": 10.1861,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.56,
|
| 18 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 19 |
+
"loss": 9.3871,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.34,
|
| 24 |
+
"learning_rate": 3e-06,
|
| 25 |
+
"loss": 8.9208,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 3.12,
|
| 30 |
+
"learning_rate": 4.000000000000001e-06,
|
| 31 |
+
"loss": 8.5062,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.9,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 7.9395,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.68,
|
| 42 |
+
"learning_rate": 6e-06,
|
| 43 |
+
"loss": 7.4515,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.47,
|
| 48 |
+
"learning_rate": 7.000000000000001e-06,
|
| 49 |
+
"loss": 6.9286,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 6.25,
|
| 54 |
+
"learning_rate": 8.000000000000001e-06,
|
| 55 |
+
"loss": 6.5255,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 7.03,
|
| 60 |
+
"learning_rate": 9e-06,
|
| 61 |
+
"loss": 6.2869,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 7.81,
|
| 66 |
+
"learning_rate": 1e-05,
|
| 67 |
+
"loss": 6.1101,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 8.59,
|
| 72 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 73 |
+
"loss": 6.0904,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 9.37,
|
| 78 |
+
"learning_rate": 1.2e-05,
|
| 79 |
+
"loss": 6.0359,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 10.16,
|
| 84 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 85 |
+
"loss": 5.9918,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.93,
|
| 90 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 91 |
+
"loss": 5.9047,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 11.71,
|
| 96 |
+
"learning_rate": 1.5e-05,
|
| 97 |
+
"loss": 5.9245,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 12.5,
|
| 102 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 103 |
+
"loss": 5.8934,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 13.28,
|
| 108 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 109 |
+
"loss": 5.872,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 14.06,
|
| 114 |
+
"learning_rate": 1.8e-05,
|
| 115 |
+
"loss": 5.8497,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 14.84,
|
| 120 |
+
"learning_rate": 1.9e-05,
|
| 121 |
+
"loss": 5.7714,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 15.62,
|
| 126 |
+
"learning_rate": 2e-05,
|
| 127 |
+
"loss": 5.8107,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 16.4,
|
| 132 |
+
"learning_rate": 2.1e-05,
|
| 133 |
+
"loss": 5.7927,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 17.19,
|
| 138 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 139 |
+
"loss": 5.7739,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 17.96,
|
| 144 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 145 |
+
"loss": 5.7129,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 18.74,
|
| 150 |
+
"learning_rate": 2.4e-05,
|
| 151 |
+
"loss": 5.7431,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 19.53,
|
| 156 |
+
"learning_rate": 2.5e-05,
|
| 157 |
+
"loss": 5.7336,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 20.31,
|
| 162 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 163 |
+
"loss": 5.7209,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 21.09,
|
| 168 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 169 |
+
"loss": 5.7094,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 21.87,
|
| 174 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 175 |
+
"loss": 5.6441,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 22.65,
|
| 180 |
+
"learning_rate": 2.9e-05,
|
| 181 |
+
"loss": 5.6845,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 23.43,
|
| 186 |
+
"learning_rate": 3e-05,
|
| 187 |
+
"loss": 5.67,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 24.22,
|
| 192 |
+
"learning_rate": 3.1e-05,
|
| 193 |
+
"loss": 5.6608,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 24.99,
|
| 198 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 199 |
+
"loss": 5.6013,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 25.78,
|
| 204 |
+
"learning_rate": 3.3e-05,
|
| 205 |
+
"loss": 5.6329,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 26.56,
|
| 210 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 211 |
+
"loss": 5.6337,
|
| 212 |
+
"step": 3400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 27.34,
|
| 216 |
+
"learning_rate": 3.5e-05,
|
| 217 |
+
"loss": 5.6169,
|
| 218 |
+
"step": 3500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 28.12,
|
| 222 |
+
"learning_rate": 3.6e-05,
|
| 223 |
+
"loss": 5.6096,
|
| 224 |
+
"step": 3600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 28.9,
|
| 228 |
+
"learning_rate": 3.7e-05,
|
| 229 |
+
"loss": 5.5511,
|
| 230 |
+
"step": 3700
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 29.68,
|
| 234 |
+
"learning_rate": 3.8e-05,
|
| 235 |
+
"loss": 5.5866,
|
| 236 |
+
"step": 3800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 30.47,
|
| 240 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 241 |
+
"loss": 5.5778,
|
| 242 |
+
"step": 3900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 31.25,
|
| 246 |
+
"learning_rate": 4e-05,
|
| 247 |
+
"loss": 5.5705,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 32.03,
|
| 252 |
+
"learning_rate": 4.1e-05,
|
| 253 |
+
"loss": 5.5586,
|
| 254 |
+
"step": 4100
|
| 255 |
+
}
|
| 256 |
+
],
|
| 257 |
+
"max_steps": 5120,
|
| 258 |
+
"num_train_epochs": 40,
|
| 259 |
+
"total_flos": 2.77949076996096e+17,
|
| 260 |
+
"trial_name": null,
|
| 261 |
+
"trial_params": null
|
| 262 |
+
}
|
checkpoint-4100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e925dd4c7ba98433a69c9c7b623ba01a2f38eb6bb66a9ad17344c1f9527c6010
|
| 3 |
+
size 3579
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 260,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 3,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"sep_token_id": 2,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.27.0.dev0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f85cc711833fe2324d79ba5328939f20e989d0eab105b23380683fc0d572619a
|
| 3 |
+
size 441897977
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e925dd4c7ba98433a69c9c7b623ba01a2f38eb6bb66a9ad17344c1f9527c6010
|
| 3 |
+
size 3579
|