Upload folder using huggingface_hub
Browse files- config.json +39 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +292 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.46.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e11fbc418ae598e4644ddfcc8d1aacbbd4230c8cb858ebc6477eaccaeee1fbd2
|
| 3 |
+
size 497774208
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c62e56f5eb0c470d90b5b1957079741b1c07c7e96923ffef46e644bc6cfde5ac
|
| 3 |
+
size 995642298
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ae02fa57f82cb7fb7b247e0767643df10e533ac18e9cfa2ba6650a626cf100
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4309da5908fa8235949ad2308f18191cdcaeda0731927ca9f52b20e758e5c8c4
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 38.22314049586777,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 18500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0330578512396693,
|
| 13 |
+
"grad_norm": 3.987211227416992,
|
| 14 |
+
"learning_rate": 4.896694214876033e-05,
|
| 15 |
+
"loss": 3.0865,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0661157024793386,
|
| 20 |
+
"grad_norm": 4.349371910095215,
|
| 21 |
+
"learning_rate": 4.793388429752066e-05,
|
| 22 |
+
"loss": 2.7313,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0991735537190084,
|
| 27 |
+
"grad_norm": 3.389904499053955,
|
| 28 |
+
"learning_rate": 4.6900826446280993e-05,
|
| 29 |
+
"loss": 2.5216,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.132231404958677,
|
| 34 |
+
"grad_norm": 4.1725382804870605,
|
| 35 |
+
"learning_rate": 4.586776859504133e-05,
|
| 36 |
+
"loss": 2.3443,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.1652892561983474,
|
| 41 |
+
"grad_norm": 3.5824990272521973,
|
| 42 |
+
"learning_rate": 4.4834710743801654e-05,
|
| 43 |
+
"loss": 2.1814,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.198347107438017,
|
| 48 |
+
"grad_norm": 3.269134283065796,
|
| 49 |
+
"learning_rate": 4.3801652892561984e-05,
|
| 50 |
+
"loss": 2.0362,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.231404958677686,
|
| 55 |
+
"grad_norm": 3.2773518562316895,
|
| 56 |
+
"learning_rate": 4.2768595041322315e-05,
|
| 57 |
+
"loss": 1.909,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.264462809917354,
|
| 62 |
+
"grad_norm": 3.609391450881958,
|
| 63 |
+
"learning_rate": 4.1735537190082645e-05,
|
| 64 |
+
"loss": 1.7989,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.297520661157025,
|
| 69 |
+
"grad_norm": 3.6867423057556152,
|
| 70 |
+
"learning_rate": 4.0702479338842975e-05,
|
| 71 |
+
"loss": 1.6884,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.330578512396695,
|
| 76 |
+
"grad_norm": 3.11508846282959,
|
| 77 |
+
"learning_rate": 3.9669421487603306e-05,
|
| 78 |
+
"loss": 1.5927,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.363636363636363,
|
| 83 |
+
"grad_norm": 3.385504961013794,
|
| 84 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 85 |
+
"loss": 1.507,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.396694214876034,
|
| 90 |
+
"grad_norm": 2.984614372253418,
|
| 91 |
+
"learning_rate": 3.760330578512397e-05,
|
| 92 |
+
"loss": 1.4295,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.429752066115702,
|
| 97 |
+
"grad_norm": 3.5454905033111572,
|
| 98 |
+
"learning_rate": 3.65702479338843e-05,
|
| 99 |
+
"loss": 1.3534,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.462809917355372,
|
| 104 |
+
"grad_norm": 3.397068738937378,
|
| 105 |
+
"learning_rate": 3.553719008264463e-05,
|
| 106 |
+
"loss": 1.2914,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.49586776859504,
|
| 111 |
+
"grad_norm": 2.902157783508301,
|
| 112 |
+
"learning_rate": 3.4504132231404964e-05,
|
| 113 |
+
"loss": 1.2266,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.52892561983471,
|
| 118 |
+
"grad_norm": 3.3206584453582764,
|
| 119 |
+
"learning_rate": 3.347107438016529e-05,
|
| 120 |
+
"loss": 1.1684,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.56198347107438,
|
| 125 |
+
"grad_norm": 3.4308412075042725,
|
| 126 |
+
"learning_rate": 3.243801652892562e-05,
|
| 127 |
+
"loss": 1.1224,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.59504132231405,
|
| 132 |
+
"grad_norm": 3.3049848079681396,
|
| 133 |
+
"learning_rate": 3.1404958677685955e-05,
|
| 134 |
+
"loss": 1.0648,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.628099173553718,
|
| 139 |
+
"grad_norm": 2.979891061782837,
|
| 140 |
+
"learning_rate": 3.0371900826446282e-05,
|
| 141 |
+
"loss": 1.0281,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 20.66115702479339,
|
| 146 |
+
"grad_norm": 3.2846224308013916,
|
| 147 |
+
"learning_rate": 2.9338842975206616e-05,
|
| 148 |
+
"loss": 0.9794,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.694214876033058,
|
| 153 |
+
"grad_norm": 2.7981956005096436,
|
| 154 |
+
"learning_rate": 2.8305785123966943e-05,
|
| 155 |
+
"loss": 0.9432,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 22.727272727272727,
|
| 160 |
+
"grad_norm": 2.4917824268341064,
|
| 161 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 162 |
+
"loss": 0.9033,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 23.760330578512395,
|
| 167 |
+
"grad_norm": 2.988530397415161,
|
| 168 |
+
"learning_rate": 2.6239669421487607e-05,
|
| 169 |
+
"loss": 0.8758,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 24.793388429752067,
|
| 174 |
+
"grad_norm": 2.985724687576294,
|
| 175 |
+
"learning_rate": 2.5206611570247934e-05,
|
| 176 |
+
"loss": 0.8401,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 25.826446280991735,
|
| 181 |
+
"grad_norm": 3.4835329055786133,
|
| 182 |
+
"learning_rate": 2.4173553719008264e-05,
|
| 183 |
+
"loss": 0.808,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 26.859504132231404,
|
| 188 |
+
"grad_norm": 2.9876391887664795,
|
| 189 |
+
"learning_rate": 2.3140495867768598e-05,
|
| 190 |
+
"loss": 0.7827,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 27.892561983471076,
|
| 195 |
+
"grad_norm": 3.131237030029297,
|
| 196 |
+
"learning_rate": 2.2107438016528928e-05,
|
| 197 |
+
"loss": 0.7582,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 28.925619834710744,
|
| 202 |
+
"grad_norm": 3.0456302165985107,
|
| 203 |
+
"learning_rate": 2.1074380165289255e-05,
|
| 204 |
+
"loss": 0.7301,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 29.958677685950413,
|
| 209 |
+
"grad_norm": 2.6555545330047607,
|
| 210 |
+
"learning_rate": 2.004132231404959e-05,
|
| 211 |
+
"loss": 0.7064,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 30.99173553719008,
|
| 216 |
+
"grad_norm": 2.8180575370788574,
|
| 217 |
+
"learning_rate": 1.900826446280992e-05,
|
| 218 |
+
"loss": 0.689,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 32.02479338842975,
|
| 223 |
+
"grad_norm": 2.7723453044891357,
|
| 224 |
+
"learning_rate": 1.797520661157025e-05,
|
| 225 |
+
"loss": 0.6673,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 33.05785123966942,
|
| 230 |
+
"grad_norm": 2.7811803817749023,
|
| 231 |
+
"learning_rate": 1.694214876033058e-05,
|
| 232 |
+
"loss": 0.6452,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 34.09090909090909,
|
| 237 |
+
"grad_norm": 2.7869203090667725,
|
| 238 |
+
"learning_rate": 1.590909090909091e-05,
|
| 239 |
+
"loss": 0.6311,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 35.12396694214876,
|
| 244 |
+
"grad_norm": 2.8924448490142822,
|
| 245 |
+
"learning_rate": 1.487603305785124e-05,
|
| 246 |
+
"loss": 0.6147,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 36.15702479338843,
|
| 251 |
+
"grad_norm": 2.880516529083252,
|
| 252 |
+
"learning_rate": 1.3842975206611573e-05,
|
| 253 |
+
"loss": 0.5963,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 37.1900826446281,
|
| 258 |
+
"grad_norm": 2.2562177181243896,
|
| 259 |
+
"learning_rate": 1.2809917355371901e-05,
|
| 260 |
+
"loss": 0.5881,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 38.22314049586777,
|
| 265 |
+
"grad_norm": 2.5836784839630127,
|
| 266 |
+
"learning_rate": 1.1776859504132231e-05,
|
| 267 |
+
"loss": 0.5742,
|
| 268 |
+
"step": 18500
|
| 269 |
+
}
|
| 270 |
+
],
|
| 271 |
+
"logging_steps": 500,
|
| 272 |
+
"max_steps": 24200,
|
| 273 |
+
"num_input_tokens_seen": 0,
|
| 274 |
+
"num_train_epochs": 50,
|
| 275 |
+
"save_steps": 500,
|
| 276 |
+
"stateful_callbacks": {
|
| 277 |
+
"TrainerControl": {
|
| 278 |
+
"args": {
|
| 279 |
+
"should_epoch_stop": false,
|
| 280 |
+
"should_evaluate": false,
|
| 281 |
+
"should_log": false,
|
| 282 |
+
"should_save": true,
|
| 283 |
+
"should_training_stop": false
|
| 284 |
+
},
|
| 285 |
+
"attributes": {}
|
| 286 |
+
}
|
| 287 |
+
},
|
| 288 |
+
"total_flos": 9665322909696000.0,
|
| 289 |
+
"train_batch_size": 8,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f1f0a9c8ed79485a88f7eb0cbec36c987573ca1de59a8f4cae4a72ca3c26cd5
|
| 3 |
+
size 5304
|