Upload folder using huggingface_hub
Browse files- config.json +31 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +499 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "silu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 256,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 768,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"max_relative_positions": -1,
|
| 14 |
+
"model_type": "deberta-v2",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 6,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pooler_dropout": 0,
|
| 19 |
+
"pooler_hidden_act": "gelu",
|
| 20 |
+
"pooler_hidden_size": 256,
|
| 21 |
+
"pos_att_type": [
|
| 22 |
+
"p2c",
|
| 23 |
+
"c2p"
|
| 24 |
+
],
|
| 25 |
+
"position_biased_input": true,
|
| 26 |
+
"relative_attention": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.33.0.dev0",
|
| 29 |
+
"type_vocab_size": 0,
|
| 30 |
+
"vocab_size": 137
|
| 31 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecd9f3083b89e2d4e734fdb148b533e2bd04da17b2ed8763e1f30c0e0581fffc
|
| 3 |
+
size 33557061
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbf02dc35db4b55bf39c73f86dce3eb51d3e06670e567b000d480325988ddbb9
|
| 3 |
+
size 16770865
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7283838f08d45afe30ca67150e994ca45680e8640b9861f3c11467fe004b1dea
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e64b28a8c5b01784ab604157a91910cc7055bcf99a6cf6ffefd4a0fb7deaa0
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.819185320199062,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.965867278325039e-05,
|
| 14 |
+
"loss": 1.8363,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 9.931734556650079e-05,
|
| 20 |
+
"loss": 1.2927,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 9.897601834975117e-05,
|
| 26 |
+
"loss": 1.0069,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 9.863469113300157e-05,
|
| 32 |
+
"loss": 0.8362,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 9.829336391625195e-05,
|
| 38 |
+
"loss": 0.7217,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.06,
|
| 43 |
+
"learning_rate": 9.795203669950235e-05,
|
| 44 |
+
"loss": 0.6462,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07,
|
| 49 |
+
"learning_rate": 9.761070948275274e-05,
|
| 50 |
+
"loss": 0.5914,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 9.726938226600313e-05,
|
| 56 |
+
"loss": 0.5497,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09,
|
| 61 |
+
"learning_rate": 9.692805504925352e-05,
|
| 62 |
+
"loss": 0.5154,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.1,
|
| 67 |
+
"learning_rate": 9.658672783250392e-05,
|
| 68 |
+
"loss": 0.4867,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.11,
|
| 73 |
+
"learning_rate": 9.62454006157543e-05,
|
| 74 |
+
"loss": 0.4628,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.12,
|
| 79 |
+
"learning_rate": 9.590407339900468e-05,
|
| 80 |
+
"loss": 0.4393,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.13,
|
| 85 |
+
"learning_rate": 9.556274618225508e-05,
|
| 86 |
+
"loss": 0.4199,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"learning_rate": 9.522141896550547e-05,
|
| 92 |
+
"loss": 0.3996,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15,
|
| 97 |
+
"learning_rate": 9.488009174875586e-05,
|
| 98 |
+
"loss": 0.383,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.16,
|
| 103 |
+
"learning_rate": 9.453876453200626e-05,
|
| 104 |
+
"loss": 0.37,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.17,
|
| 109 |
+
"learning_rate": 9.419743731525666e-05,
|
| 110 |
+
"loss": 0.3577,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.18,
|
| 115 |
+
"learning_rate": 9.385611009850704e-05,
|
| 116 |
+
"loss": 0.3468,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.19,
|
| 121 |
+
"learning_rate": 9.351478288175744e-05,
|
| 122 |
+
"loss": 0.3364,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2,
|
| 127 |
+
"learning_rate": 9.317345566500783e-05,
|
| 128 |
+
"loss": 0.3281,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"learning_rate": 9.283212844825821e-05,
|
| 134 |
+
"loss": 0.3198,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.23,
|
| 139 |
+
"learning_rate": 9.249080123150861e-05,
|
| 140 |
+
"loss": 0.3124,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.24,
|
| 145 |
+
"learning_rate": 9.214947401475899e-05,
|
| 146 |
+
"loss": 0.3061,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.25,
|
| 151 |
+
"learning_rate": 9.180814679800939e-05,
|
| 152 |
+
"loss": 0.2999,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.26,
|
| 157 |
+
"learning_rate": 9.146681958125977e-05,
|
| 158 |
+
"loss": 0.2938,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.27,
|
| 163 |
+
"learning_rate": 9.112549236451017e-05,
|
| 164 |
+
"loss": 0.2886,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.28,
|
| 169 |
+
"learning_rate": 9.078416514776056e-05,
|
| 170 |
+
"loss": 0.2834,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.29,
|
| 175 |
+
"learning_rate": 9.044283793101095e-05,
|
| 176 |
+
"loss": 0.2791,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3,
|
| 181 |
+
"learning_rate": 9.010151071426134e-05,
|
| 182 |
+
"loss": 0.2748,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.31,
|
| 187 |
+
"learning_rate": 8.976018349751174e-05,
|
| 188 |
+
"loss": 0.2708,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.32,
|
| 193 |
+
"learning_rate": 8.941885628076212e-05,
|
| 194 |
+
"loss": 0.2673,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.33,
|
| 199 |
+
"learning_rate": 8.90775290640125e-05,
|
| 200 |
+
"loss": 0.2634,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.34,
|
| 205 |
+
"learning_rate": 8.87362018472629e-05,
|
| 206 |
+
"loss": 0.2604,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.35,
|
| 211 |
+
"learning_rate": 8.839487463051329e-05,
|
| 212 |
+
"loss": 0.2575,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.36,
|
| 217 |
+
"learning_rate": 8.805354741376368e-05,
|
| 218 |
+
"loss": 0.2542,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.37,
|
| 223 |
+
"learning_rate": 8.771222019701407e-05,
|
| 224 |
+
"loss": 0.251,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.38,
|
| 229 |
+
"learning_rate": 8.737089298026447e-05,
|
| 230 |
+
"loss": 0.2483,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.39,
|
| 235 |
+
"learning_rate": 8.702956576351485e-05,
|
| 236 |
+
"loss": 0.2458,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.4,
|
| 241 |
+
"learning_rate": 8.668823854676525e-05,
|
| 242 |
+
"loss": 0.2429,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.41,
|
| 247 |
+
"learning_rate": 8.634691133001563e-05,
|
| 248 |
+
"loss": 0.2405,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.42,
|
| 253 |
+
"learning_rate": 8.600558411326603e-05,
|
| 254 |
+
"loss": 0.2391,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.43,
|
| 259 |
+
"learning_rate": 8.566425689651641e-05,
|
| 260 |
+
"loss": 0.237,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.44,
|
| 265 |
+
"learning_rate": 8.532292967976681e-05,
|
| 266 |
+
"loss": 0.2342,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.45,
|
| 271 |
+
"learning_rate": 8.49816024630172e-05,
|
| 272 |
+
"loss": 0.2326,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.46,
|
| 277 |
+
"learning_rate": 8.464027524626758e-05,
|
| 278 |
+
"loss": 0.2304,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.47,
|
| 283 |
+
"learning_rate": 8.429894802951798e-05,
|
| 284 |
+
"loss": 0.2286,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.48,
|
| 289 |
+
"learning_rate": 8.395762081276836e-05,
|
| 290 |
+
"loss": 0.2271,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.49,
|
| 295 |
+
"learning_rate": 8.361629359601877e-05,
|
| 296 |
+
"loss": 0.2252,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5,
|
| 301 |
+
"learning_rate": 8.327496637926916e-05,
|
| 302 |
+
"loss": 0.2231,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.51,
|
| 307 |
+
"learning_rate": 8.293363916251956e-05,
|
| 308 |
+
"loss": 0.2219,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.52,
|
| 313 |
+
"learning_rate": 8.259231194576994e-05,
|
| 314 |
+
"loss": 0.2199,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.53,
|
| 319 |
+
"learning_rate": 8.225098472902032e-05,
|
| 320 |
+
"loss": 0.219,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.54,
|
| 325 |
+
"learning_rate": 8.190965751227072e-05,
|
| 326 |
+
"loss": 0.2169,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.55,
|
| 331 |
+
"learning_rate": 8.15683302955211e-05,
|
| 332 |
+
"loss": 0.2157,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.56,
|
| 337 |
+
"learning_rate": 8.12270030787715e-05,
|
| 338 |
+
"loss": 0.214,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.57,
|
| 343 |
+
"learning_rate": 8.088567586202189e-05,
|
| 344 |
+
"loss": 0.2129,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.58,
|
| 349 |
+
"learning_rate": 8.054434864527229e-05,
|
| 350 |
+
"loss": 0.2117,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.59,
|
| 355 |
+
"learning_rate": 8.020302142852267e-05,
|
| 356 |
+
"loss": 0.2111,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.6,
|
| 361 |
+
"learning_rate": 7.986169421177307e-05,
|
| 362 |
+
"loss": 0.2091,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.61,
|
| 367 |
+
"learning_rate": 7.952036699502345e-05,
|
| 368 |
+
"loss": 0.2084,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.62,
|
| 373 |
+
"learning_rate": 7.917903977827385e-05,
|
| 374 |
+
"loss": 0.2071,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.63,
|
| 379 |
+
"learning_rate": 7.883771256152423e-05,
|
| 380 |
+
"loss": 0.2057,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.65,
|
| 385 |
+
"learning_rate": 7.849638534477462e-05,
|
| 386 |
+
"loss": 0.2051,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.66,
|
| 391 |
+
"learning_rate": 7.815505812802502e-05,
|
| 392 |
+
"loss": 0.2036,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.67,
|
| 397 |
+
"learning_rate": 7.78137309112754e-05,
|
| 398 |
+
"loss": 0.2027,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.68,
|
| 403 |
+
"learning_rate": 7.74724036945258e-05,
|
| 404 |
+
"loss": 0.2017,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.69,
|
| 409 |
+
"learning_rate": 7.713107647777618e-05,
|
| 410 |
+
"loss": 0.2009,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.7,
|
| 415 |
+
"learning_rate": 7.678974926102658e-05,
|
| 416 |
+
"loss": 0.2003,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.71,
|
| 421 |
+
"learning_rate": 7.644842204427697e-05,
|
| 422 |
+
"loss": 0.1991,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.72,
|
| 427 |
+
"learning_rate": 7.610709482752736e-05,
|
| 428 |
+
"loss": 0.198,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.73,
|
| 433 |
+
"learning_rate": 7.576576761077775e-05,
|
| 434 |
+
"loss": 0.1974,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.74,
|
| 439 |
+
"learning_rate": 7.542444039402814e-05,
|
| 440 |
+
"loss": 0.1964,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.75,
|
| 445 |
+
"learning_rate": 7.508311317727853e-05,
|
| 446 |
+
"loss": 0.1958,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.76,
|
| 451 |
+
"learning_rate": 7.474178596052893e-05,
|
| 452 |
+
"loss": 0.1949,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.77,
|
| 457 |
+
"learning_rate": 7.440045874377931e-05,
|
| 458 |
+
"loss": 0.1937,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.78,
|
| 463 |
+
"learning_rate": 7.40591315270297e-05,
|
| 464 |
+
"loss": 0.1931,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.79,
|
| 469 |
+
"learning_rate": 7.37178043102801e-05,
|
| 470 |
+
"loss": 0.1926,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8,
|
| 475 |
+
"learning_rate": 7.337647709353048e-05,
|
| 476 |
+
"loss": 0.1919,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.81,
|
| 481 |
+
"learning_rate": 7.303514987678088e-05,
|
| 482 |
+
"loss": 0.1909,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.82,
|
| 487 |
+
"learning_rate": 7.269382266003127e-05,
|
| 488 |
+
"loss": 0.1902,
|
| 489 |
+
"step": 40000
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"logging_steps": 500,
|
| 493 |
+
"max_steps": 146487,
|
| 494 |
+
"num_train_epochs": 3,
|
| 495 |
+
"save_steps": 10000,
|
| 496 |
+
"total_flos": 2.527620759552e+17,
|
| 497 |
+
"trial_name": null,
|
| 498 |
+
"trial_params": null
|
| 499 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40c0e0320e43690326bfc331e5b4fdfc33afc9058cdc44e8090b63a8a1819701
|
| 3 |
+
size 4027
|