first commit
Browse files- config.json +41 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- trainer_state.json +337 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/storage/home/lanzhenzhongLab/zhangdehao/zhf/chai_comp/models/gpt2-large",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2ForSequenceClassification"
|
| 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": 1280,
|
| 16 |
+
"n_head": 20,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 36,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"pad_token_id": 50256,
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.32.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:067e7c5be2bd7735700f30da203f75f3a3e48f26928d38020a93501335a09523
|
| 3 |
+
size 6192647080
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae9bec07817320f86f6f37df115c20ab2c69c9752fa4ae830941197d41900255
|
| 3 |
+
size 3096273121
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:996fc1752e98bd1788beee32391e278361d3c0b2768885e07f29eadf775692be
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dc76a17dec037e439fe433ed44ecd74de2d30dd3069e8b9972f52197949ab1e
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.991983741673253,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 26500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.991265511472117e-05,
|
| 14 |
+
"loss": 0.7257,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 9.965092562404402e-05,
|
| 20 |
+
"loss": 0.6831,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 9.921572595726207e-05,
|
| 26 |
+
"loss": 0.6848,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 9.860857661297404e-05,
|
| 32 |
+
"loss": 0.701,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.28,
|
| 37 |
+
"learning_rate": 9.78315988467729e-05,
|
| 38 |
+
"loss": 0.683,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.34,
|
| 43 |
+
"learning_rate": 9.688750726001277e-05,
|
| 44 |
+
"loss": 0.6754,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4,
|
| 49 |
+
"learning_rate": 9.577960031554716e-05,
|
| 50 |
+
"loss": 0.6712,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.45,
|
| 55 |
+
"learning_rate": 9.451174881357465e-05,
|
| 56 |
+
"loss": 0.67,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.51,
|
| 61 |
+
"learning_rate": 9.308838236785487e-05,
|
| 62 |
+
"loss": 0.6698,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.56,
|
| 67 |
+
"learning_rate": 9.151447392954424e-05,
|
| 68 |
+
"loss": 0.6652,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.62,
|
| 73 |
+
"learning_rate": 8.979552241272211e-05,
|
| 74 |
+
"loss": 0.6552,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.68,
|
| 79 |
+
"learning_rate": 8.793753348230996e-05,
|
| 80 |
+
"loss": 0.665,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.73,
|
| 85 |
+
"learning_rate": 8.594699857150682e-05,
|
| 86 |
+
"loss": 0.6618,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.79,
|
| 91 |
+
"learning_rate": 8.383087220204982e-05,
|
| 92 |
+
"loss": 0.6589,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.85,
|
| 97 |
+
"learning_rate": 8.159654768653795e-05,
|
| 98 |
+
"loss": 0.6518,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.9,
|
| 103 |
+
"learning_rate": 7.925183129771058e-05,
|
| 104 |
+
"loss": 0.6455,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.96,
|
| 109 |
+
"learning_rate": 7.680491499492743e-05,
|
| 110 |
+
"loss": 0.6539,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.02,
|
| 115 |
+
"learning_rate": 7.426434780313864e-05,
|
| 116 |
+
"loss": 0.6527,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.07,
|
| 121 |
+
"learning_rate": 7.163900594434061e-05,
|
| 122 |
+
"loss": 0.6337,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.13,
|
| 127 |
+
"learning_rate": 6.893806182587231e-05,
|
| 128 |
+
"loss": 0.6364,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.19,
|
| 133 |
+
"learning_rate": 6.617095199390065e-05,
|
| 134 |
+
"loss": 0.6361,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.24,
|
| 139 |
+
"learning_rate": 6.334734416405869e-05,
|
| 140 |
+
"loss": 0.6415,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.3,
|
| 145 |
+
"learning_rate": 6.047710344442528e-05,
|
| 146 |
+
"loss": 0.6392,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.35,
|
| 151 |
+
"learning_rate": 5.7570257868855534e-05,
|
| 152 |
+
"loss": 0.63,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.41,
|
| 157 |
+
"learning_rate": 5.463696336108234e-05,
|
| 158 |
+
"loss": 0.6351,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.47,
|
| 163 |
+
"learning_rate": 5.168746825199652e-05,
|
| 164 |
+
"loss": 0.6387,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.52,
|
| 169 |
+
"learning_rate": 4.873207747407539e-05,
|
| 170 |
+
"loss": 0.6367,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.58,
|
| 175 |
+
"learning_rate": 4.5781116558057044e-05,
|
| 176 |
+
"loss": 0.6361,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.64,
|
| 181 |
+
"learning_rate": 4.2844895557648356e-05,
|
| 182 |
+
"loss": 0.6322,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.69,
|
| 187 |
+
"learning_rate": 3.9933673028306675e-05,
|
| 188 |
+
"loss": 0.6346,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.75,
|
| 193 |
+
"learning_rate": 3.705762018594586e-05,
|
| 194 |
+
"loss": 0.6292,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.81,
|
| 199 |
+
"learning_rate": 3.4226785370788796e-05,
|
| 200 |
+
"loss": 0.6369,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.86,
|
| 205 |
+
"learning_rate": 3.145105894052242e-05,
|
| 206 |
+
"loss": 0.6364,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.92,
|
| 211 |
+
"learning_rate": 2.8740138715411413e-05,
|
| 212 |
+
"loss": 0.6237,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.98,
|
| 217 |
+
"learning_rate": 2.6103496096098247e-05,
|
| 218 |
+
"loss": 0.6326,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.03,
|
| 223 |
+
"learning_rate": 2.3550342972467158e-05,
|
| 224 |
+
"loss": 0.603,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.09,
|
| 229 |
+
"learning_rate": 2.108959953918542e-05,
|
| 230 |
+
"loss": 0.5948,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.15,
|
| 235 |
+
"learning_rate": 1.8729863130368315e-05,
|
| 236 |
+
"loss": 0.5824,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.2,
|
| 241 |
+
"learning_rate": 1.6479378182252464e-05,
|
| 242 |
+
"loss": 0.5755,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.26,
|
| 247 |
+
"learning_rate": 1.4346007428822483e-05,
|
| 248 |
+
"loss": 0.5733,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.31,
|
| 253 |
+
"learning_rate": 1.2337204431026971e-05,
|
| 254 |
+
"loss": 0.5754,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.37,
|
| 259 |
+
"learning_rate": 1.0459987535561556e-05,
|
| 260 |
+
"loss": 0.5756,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.43,
|
| 265 |
+
"learning_rate": 8.720915354201348e-06,
|
| 266 |
+
"loss": 0.581,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.48,
|
| 271 |
+
"learning_rate": 7.126063849353265e-06,
|
| 272 |
+
"loss": 0.5799,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.54,
|
| 277 |
+
"learning_rate": 5.681005105886394e-06,
|
| 278 |
+
"loss": 0.5749,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.6,
|
| 283 |
+
"learning_rate": 4.3907878634075136e-06,
|
| 284 |
+
"loss": 0.5698,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.65,
|
| 289 |
+
"learning_rate": 3.2599198769977968e-06,
|
| 290 |
+
"loss": 0.58,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.71,
|
| 295 |
+
"learning_rate": 2.2923521680387695e-06,
|
| 296 |
+
"loss": 0.5822,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.77,
|
| 301 |
+
"learning_rate": 1.4914652201519775e-06,
|
| 302 |
+
"loss": 0.5811,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.82,
|
| 307 |
+
"learning_rate": 8.60057168480799e-07,
|
| 308 |
+
"loss": 0.575,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.88,
|
| 313 |
+
"learning_rate": 4.0033402357874116e-07,
|
| 314 |
+
"loss": 0.5826,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.94,
|
| 319 |
+
"learning_rate": 1.1390196405984821e-07,
|
| 320 |
+
"loss": 0.5815,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.99,
|
| 325 |
+
"learning_rate": 1.761724939280951e-09,
|
| 326 |
+
"loss": 0.572,
|
| 327 |
+
"step": 26500
|
| 328 |
+
}
|
| 329 |
+
],
|
| 330 |
+
"logging_steps": 500,
|
| 331 |
+
"max_steps": 26571,
|
| 332 |
+
"num_train_epochs": 3,
|
| 333 |
+
"save_steps": 500,
|
| 334 |
+
"total_flos": 5.6664768272031744e+17,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f4f22b1b01882a6571ad58f72c1913e85f06d0a7cd690109bf15e52c2c533dc
|
| 3 |
+
size 4091
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|