Initial commit
Browse files- config.json +43 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- trainer_state.json +496 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"gradient_checkpointing": false,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_epsilon": 1e-05,
|
| 21 |
+
"model_type": "gpt2",
|
| 22 |
+
"n_ctx": 1024,
|
| 23 |
+
"n_embd": 768,
|
| 24 |
+
"n_head": 12,
|
| 25 |
+
"n_inner": null,
|
| 26 |
+
"n_layer": 6,
|
| 27 |
+
"n_positions": 1024,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"summary_activation": null,
|
| 30 |
+
"summary_first_dropout": 0.1,
|
| 31 |
+
"summary_proj_to_labels": true,
|
| 32 |
+
"summary_type": "cls_index",
|
| 33 |
+
"summary_use_proj": true,
|
| 34 |
+
"task_specific_params": {
|
| 35 |
+
"text-generation": {
|
| 36 |
+
"do_sample": true,
|
| 37 |
+
"max_length": 50
|
| 38 |
+
}
|
| 39 |
+
},
|
| 40 |
+
"transformers_version": "4.2.2",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f839ffaae95ea68e52816a1288714ea59f387d8b68a79e852861c54110554526
|
| 3 |
+
size 655348359
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b665160ab3085d25a0cd6329a2e4f02ec753f44aaca78d52a512e163d72ba70
|
| 3 |
+
size 333975623
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f298adb105fb05d6a4df51da846e22eb95ca7b58d04d2df23159a20305d8c4b
|
| 3 |
+
size 623
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.934937124111537,
|
| 5 |
+
"global_step": 40000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 3.4081,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 4.999316473000684e-05,
|
| 19 |
+
"loss": 3.3326,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.41,
|
| 24 |
+
"learning_rate": 4.998632946001368e-05,
|
| 25 |
+
"loss": 3.3069,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.55,
|
| 30 |
+
"learning_rate": 4.997949419002051e-05,
|
| 31 |
+
"loss": 3.2839,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.68,
|
| 36 |
+
"learning_rate": 4.997265892002734e-05,
|
| 37 |
+
"loss": 3.2691,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.82,
|
| 42 |
+
"learning_rate": 4.9965823650034176e-05,
|
| 43 |
+
"loss": 3.2595,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.96,
|
| 48 |
+
"learning_rate": 4.995898838004102e-05,
|
| 49 |
+
"loss": 3.2534,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.09,
|
| 54 |
+
"learning_rate": 4.995215311004785e-05,
|
| 55 |
+
"loss": 3.2124,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.23,
|
| 60 |
+
"learning_rate": 4.994531784005468e-05,
|
| 61 |
+
"loss": 3.1981,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.37,
|
| 66 |
+
"learning_rate": 4.9938482570061516e-05,
|
| 67 |
+
"loss": 3.193,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.5,
|
| 72 |
+
"learning_rate": 4.993164730006836e-05,
|
| 73 |
+
"loss": 3.1885,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.64,
|
| 78 |
+
"learning_rate": 4.992481203007519e-05,
|
| 79 |
+
"loss": 3.1881,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.78,
|
| 84 |
+
"learning_rate": 4.991797676008203e-05,
|
| 85 |
+
"loss": 3.192,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.91,
|
| 90 |
+
"learning_rate": 4.991114149008886e-05,
|
| 91 |
+
"loss": 3.181,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.05,
|
| 96 |
+
"learning_rate": 4.9904306220095696e-05,
|
| 97 |
+
"loss": 3.1629,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.19,
|
| 102 |
+
"learning_rate": 4.989747095010253e-05,
|
| 103 |
+
"loss": 3.139,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.32,
|
| 108 |
+
"learning_rate": 4.9890635680109366e-05,
|
| 109 |
+
"loss": 3.1355,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.46,
|
| 114 |
+
"learning_rate": 4.98838004101162e-05,
|
| 115 |
+
"loss": 3.1403,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.6,
|
| 120 |
+
"learning_rate": 4.9876965140123035e-05,
|
| 121 |
+
"loss": 3.1403,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.73,
|
| 126 |
+
"learning_rate": 4.987012987012987e-05,
|
| 127 |
+
"loss": 3.1366,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.87,
|
| 132 |
+
"learning_rate": 4.9863294600136705e-05,
|
| 133 |
+
"loss": 3.1378,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.01,
|
| 138 |
+
"learning_rate": 4.985645933014355e-05,
|
| 139 |
+
"loss": 3.132,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.14,
|
| 144 |
+
"learning_rate": 4.984962406015038e-05,
|
| 145 |
+
"loss": 3.0939,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.28,
|
| 150 |
+
"learning_rate": 4.9842788790157216e-05,
|
| 151 |
+
"loss": 3.0984,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.42,
|
| 156 |
+
"learning_rate": 4.9835953520164044e-05,
|
| 157 |
+
"loss": 3.0947,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.55,
|
| 162 |
+
"learning_rate": 4.9829118250170886e-05,
|
| 163 |
+
"loss": 3.099,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.69,
|
| 168 |
+
"learning_rate": 4.982228298017772e-05,
|
| 169 |
+
"loss": 3.1002,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.83,
|
| 174 |
+
"learning_rate": 4.9815447710184555e-05,
|
| 175 |
+
"loss": 3.0929,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.96,
|
| 180 |
+
"learning_rate": 4.980861244019139e-05,
|
| 181 |
+
"loss": 3.1047,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.1,
|
| 186 |
+
"learning_rate": 4.9801777170198225e-05,
|
| 187 |
+
"loss": 3.0691,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.24,
|
| 192 |
+
"learning_rate": 4.979494190020506e-05,
|
| 193 |
+
"loss": 3.0629,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.37,
|
| 198 |
+
"learning_rate": 4.9788106630211895e-05,
|
| 199 |
+
"loss": 3.0655,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.51,
|
| 204 |
+
"learning_rate": 4.978127136021873e-05,
|
| 205 |
+
"loss": 3.0679,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.65,
|
| 210 |
+
"learning_rate": 4.977443609022557e-05,
|
| 211 |
+
"loss": 3.063,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.78,
|
| 216 |
+
"learning_rate": 4.97676008202324e-05,
|
| 217 |
+
"loss": 3.065,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.92,
|
| 222 |
+
"learning_rate": 4.9760765550239234e-05,
|
| 223 |
+
"loss": 3.0706,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.06,
|
| 228 |
+
"learning_rate": 4.975393028024607e-05,
|
| 229 |
+
"loss": 3.0469,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.19,
|
| 234 |
+
"learning_rate": 4.974709501025291e-05,
|
| 235 |
+
"loss": 3.0315,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.33,
|
| 240 |
+
"learning_rate": 4.9740259740259745e-05,
|
| 241 |
+
"loss": 3.0287,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.47,
|
| 246 |
+
"learning_rate": 4.973342447026658e-05,
|
| 247 |
+
"loss": 3.0319,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.6,
|
| 252 |
+
"learning_rate": 4.9726589200273414e-05,
|
| 253 |
+
"loss": 3.0376,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.74,
|
| 258 |
+
"learning_rate": 4.971975393028025e-05,
|
| 259 |
+
"loss": 3.0405,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.88,
|
| 264 |
+
"learning_rate": 4.9712918660287084e-05,
|
| 265 |
+
"loss": 3.0393,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.01,
|
| 270 |
+
"learning_rate": 4.970608339029392e-05,
|
| 271 |
+
"loss": 3.0358,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.15,
|
| 276 |
+
"learning_rate": 4.9699248120300754e-05,
|
| 277 |
+
"loss": 3.0,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.29,
|
| 282 |
+
"learning_rate": 4.969241285030759e-05,
|
| 283 |
+
"loss": 3.0069,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.42,
|
| 288 |
+
"learning_rate": 4.968557758031442e-05,
|
| 289 |
+
"loss": 3.0053,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.56,
|
| 294 |
+
"learning_rate": 4.967874231032126e-05,
|
| 295 |
+
"loss": 3.0082,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.7,
|
| 300 |
+
"learning_rate": 4.96719070403281e-05,
|
| 301 |
+
"loss": 3.0102,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.83,
|
| 306 |
+
"learning_rate": 4.9665071770334934e-05,
|
| 307 |
+
"loss": 3.017,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.97,
|
| 312 |
+
"learning_rate": 4.965823650034176e-05,
|
| 313 |
+
"loss": 3.0128,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.11,
|
| 318 |
+
"learning_rate": 4.96514012303486e-05,
|
| 319 |
+
"loss": 2.9722,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.24,
|
| 324 |
+
"learning_rate": 4.964456596035544e-05,
|
| 325 |
+
"loss": 2.9764,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.38,
|
| 330 |
+
"learning_rate": 4.9637730690362274e-05,
|
| 331 |
+
"loss": 2.9836,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.52,
|
| 336 |
+
"learning_rate": 4.963089542036911e-05,
|
| 337 |
+
"loss": 2.9837,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.65,
|
| 342 |
+
"learning_rate": 4.9624060150375936e-05,
|
| 343 |
+
"loss": 2.9803,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 7.79,
|
| 348 |
+
"learning_rate": 4.961722488038278e-05,
|
| 349 |
+
"loss": 2.9923,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 7.93,
|
| 354 |
+
"learning_rate": 4.961038961038961e-05,
|
| 355 |
+
"loss": 2.9973,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 8.06,
|
| 360 |
+
"learning_rate": 4.960355434039645e-05,
|
| 361 |
+
"loss": 2.9631,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 8.2,
|
| 366 |
+
"learning_rate": 4.959671907040329e-05,
|
| 367 |
+
"loss": 2.9481,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.34,
|
| 372 |
+
"learning_rate": 4.958988380041012e-05,
|
| 373 |
+
"loss": 2.9594,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.47,
|
| 378 |
+
"learning_rate": 4.958304853041695e-05,
|
| 379 |
+
"loss": 2.9552,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.61,
|
| 384 |
+
"learning_rate": 4.957621326042379e-05,
|
| 385 |
+
"loss": 2.9616,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.75,
|
| 390 |
+
"learning_rate": 4.956937799043063e-05,
|
| 391 |
+
"loss": 2.9692,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.88,
|
| 396 |
+
"learning_rate": 4.956254272043746e-05,
|
| 397 |
+
"loss": 2.9657,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.02,
|
| 402 |
+
"learning_rate": 4.955570745044429e-05,
|
| 403 |
+
"loss": 2.9617,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.16,
|
| 408 |
+
"learning_rate": 4.9548872180451126e-05,
|
| 409 |
+
"loss": 2.9246,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 9.29,
|
| 414 |
+
"learning_rate": 4.954203691045797e-05,
|
| 415 |
+
"loss": 2.9305,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.43,
|
| 420 |
+
"learning_rate": 4.95352016404648e-05,
|
| 421 |
+
"loss": 2.9364,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.57,
|
| 426 |
+
"learning_rate": 4.952836637047164e-05,
|
| 427 |
+
"loss": 2.9419,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 9.7,
|
| 432 |
+
"learning_rate": 4.952153110047847e-05,
|
| 433 |
+
"loss": 2.9498,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 9.84,
|
| 438 |
+
"learning_rate": 4.951469583048531e-05,
|
| 439 |
+
"loss": 2.9423,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.98,
|
| 444 |
+
"learning_rate": 4.950786056049214e-05,
|
| 445 |
+
"loss": 2.9388,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 10.11,
|
| 450 |
+
"learning_rate": 4.9501025290498976e-05,
|
| 451 |
+
"loss": 2.908,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.25,
|
| 456 |
+
"learning_rate": 4.949419002050582e-05,
|
| 457 |
+
"loss": 2.9081,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 10.39,
|
| 462 |
+
"learning_rate": 4.9487354750512646e-05,
|
| 463 |
+
"loss": 2.9072,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 10.52,
|
| 468 |
+
"learning_rate": 4.948051948051948e-05,
|
| 469 |
+
"loss": 2.9194,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 10.66,
|
| 474 |
+
"learning_rate": 4.9473684210526315e-05,
|
| 475 |
+
"loss": 2.9226,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 10.8,
|
| 480 |
+
"learning_rate": 4.946684894053316e-05,
|
| 481 |
+
"loss": 2.9242,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 10.93,
|
| 486 |
+
"learning_rate": 4.946001367053999e-05,
|
| 487 |
+
"loss": 2.9218,
|
| 488 |
+
"step": 40000
|
| 489 |
+
}
|
| 490 |
+
],
|
| 491 |
+
"max_steps": 3658000,
|
| 492 |
+
"num_train_epochs": 1000,
|
| 493 |
+
"total_flos": 80519564179537920,
|
| 494 |
+
"trial_name": null,
|
| 495 |
+
"trial_params": null
|
| 496 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de9489fac2f14250e50fa2a63af758c02ca79ea7bab0aafbc4bf3031f6c6dcff
|
| 3 |
+
size 2031
|