Upload model
Browse files- .gitattributes +2 -1
- config.json +36 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +398 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
|
| 2 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
@@ -6,3 +6,4 @@
|
|
| 6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 1 |
+
du -sh =*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"text-generation": {
|
| 29 |
+
"do_sample": true,
|
| 30 |
+
"max_length": 50
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"transformers_version": "4.2.1",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 50257
|
| 36 |
+
}
|
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 sha256:27fdaedcd285b8e92caf2ea57547986c5281509b50ee3274fa0ac4f085cc2b93
|
| 3 |
+
size 995608822
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db38845bee19c9dae895025399958bf5305dc2b3315156d0fddd091ca3b4d3f8
|
| 3 |
+
size 510406265
|
scheduler.pt
ADDED
|
Binary file (623 Bytes). View file
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,398 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.922136886324097,
|
| 5 |
+
"global_step": 116000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.999957567785463e-05,
|
| 13 |
+
"loss": 2.0156,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 4.915135570925447e-05,
|
| 19 |
+
"loss": 1.305,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 4.8302711418508934e-05,
|
| 25 |
+
"loss": 1.1809,
|
| 26 |
+
"step": 4000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"learning_rate": 4.74540671277634e-05,
|
| 31 |
+
"loss": 1.1207,
|
| 32 |
+
"step": 6000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.34,
|
| 36 |
+
"learning_rate": 4.6605422837017866e-05,
|
| 37 |
+
"loss": 1.0869,
|
| 38 |
+
"step": 8000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.42,
|
| 42 |
+
"learning_rate": 4.575677854627233e-05,
|
| 43 |
+
"loss": 1.0604,
|
| 44 |
+
"step": 10000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.51,
|
| 48 |
+
"learning_rate": 4.49081342555268e-05,
|
| 49 |
+
"loss": 1.0425,
|
| 50 |
+
"step": 12000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.59,
|
| 54 |
+
"learning_rate": 4.4059489964781264e-05,
|
| 55 |
+
"loss": 1.0303,
|
| 56 |
+
"step": 14000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.68,
|
| 60 |
+
"learning_rate": 4.321084567403573e-05,
|
| 61 |
+
"loss": 1.0101,
|
| 62 |
+
"step": 16000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.76,
|
| 66 |
+
"learning_rate": 4.2362201383290196e-05,
|
| 67 |
+
"loss": 0.9935,
|
| 68 |
+
"step": 18000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.85,
|
| 72 |
+
"learning_rate": 4.151355709254466e-05,
|
| 73 |
+
"loss": 0.9833,
|
| 74 |
+
"step": 20000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.93,
|
| 78 |
+
"learning_rate": 4.066491280179913e-05,
|
| 79 |
+
"loss": 0.9833,
|
| 80 |
+
"step": 22000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_loss": 1.1714409589767456,
|
| 85 |
+
"eval_runtime": 285.104,
|
| 86 |
+
"eval_samples_per_second": 50.936,
|
| 87 |
+
"step": 23567
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.02,
|
| 91 |
+
"learning_rate": 3.9816268511053594e-05,
|
| 92 |
+
"loss": 0.9653,
|
| 93 |
+
"step": 24000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.1,
|
| 97 |
+
"learning_rate": 3.896762422030806e-05,
|
| 98 |
+
"loss": 0.9378,
|
| 99 |
+
"step": 26000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.19,
|
| 103 |
+
"learning_rate": 3.8118979929562526e-05,
|
| 104 |
+
"loss": 0.9398,
|
| 105 |
+
"step": 28000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.27,
|
| 109 |
+
"learning_rate": 3.727033563881699e-05,
|
| 110 |
+
"loss": 0.9269,
|
| 111 |
+
"step": 30000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.36,
|
| 115 |
+
"learning_rate": 3.642169134807146e-05,
|
| 116 |
+
"loss": 0.9311,
|
| 117 |
+
"step": 32000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.44,
|
| 121 |
+
"learning_rate": 3.5573047057325924e-05,
|
| 122 |
+
"loss": 0.9179,
|
| 123 |
+
"step": 34000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.53,
|
| 127 |
+
"learning_rate": 3.472440276658039e-05,
|
| 128 |
+
"loss": 0.91,
|
| 129 |
+
"step": 36000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.61,
|
| 133 |
+
"learning_rate": 3.3875758475834856e-05,
|
| 134 |
+
"loss": 0.9146,
|
| 135 |
+
"step": 38000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.7,
|
| 139 |
+
"learning_rate": 3.302711418508932e-05,
|
| 140 |
+
"loss": 0.9101,
|
| 141 |
+
"step": 40000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.78,
|
| 145 |
+
"learning_rate": 3.217846989434379e-05,
|
| 146 |
+
"loss": 0.9024,
|
| 147 |
+
"step": 42000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.87,
|
| 151 |
+
"learning_rate": 3.132982560359825e-05,
|
| 152 |
+
"loss": 0.9078,
|
| 153 |
+
"step": 44000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.95,
|
| 157 |
+
"learning_rate": 3.048118131285272e-05,
|
| 158 |
+
"loss": 0.8919,
|
| 159 |
+
"step": 46000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.0,
|
| 163 |
+
"eval_loss": 1.1437541246414185,
|
| 164 |
+
"eval_runtime": 285.2156,
|
| 165 |
+
"eval_samples_per_second": 50.916,
|
| 166 |
+
"step": 47134
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.04,
|
| 170 |
+
"learning_rate": 2.9632537022107186e-05,
|
| 171 |
+
"loss": 0.8866,
|
| 172 |
+
"step": 48000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.12,
|
| 176 |
+
"learning_rate": 2.878389273136165e-05,
|
| 177 |
+
"loss": 0.876,
|
| 178 |
+
"step": 50000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.21,
|
| 182 |
+
"learning_rate": 2.793524844061612e-05,
|
| 183 |
+
"loss": 0.8733,
|
| 184 |
+
"step": 52000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.29,
|
| 188 |
+
"learning_rate": 2.708660414987058e-05,
|
| 189 |
+
"loss": 0.8685,
|
| 190 |
+
"step": 54000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.38,
|
| 194 |
+
"learning_rate": 2.623795985912505e-05,
|
| 195 |
+
"loss": 0.8666,
|
| 196 |
+
"step": 56000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.46,
|
| 200 |
+
"learning_rate": 2.5389315568379513e-05,
|
| 201 |
+
"loss": 0.8661,
|
| 202 |
+
"step": 58000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.55,
|
| 206 |
+
"learning_rate": 2.4540671277633982e-05,
|
| 207 |
+
"loss": 0.8542,
|
| 208 |
+
"step": 60000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.63,
|
| 212 |
+
"learning_rate": 2.3692026986888445e-05,
|
| 213 |
+
"loss": 0.8638,
|
| 214 |
+
"step": 62000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.72,
|
| 218 |
+
"learning_rate": 2.284338269614291e-05,
|
| 219 |
+
"loss": 0.854,
|
| 220 |
+
"step": 64000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.8,
|
| 224 |
+
"learning_rate": 2.1994738405397377e-05,
|
| 225 |
+
"loss": 0.8596,
|
| 226 |
+
"step": 66000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.89,
|
| 230 |
+
"learning_rate": 2.1146094114651846e-05,
|
| 231 |
+
"loss": 0.8566,
|
| 232 |
+
"step": 68000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.97,
|
| 236 |
+
"learning_rate": 2.0297449823906312e-05,
|
| 237 |
+
"loss": 0.8531,
|
| 238 |
+
"step": 70000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.0,
|
| 242 |
+
"eval_loss": 1.1323479413986206,
|
| 243 |
+
"eval_runtime": 285.2208,
|
| 244 |
+
"eval_samples_per_second": 50.915,
|
| 245 |
+
"step": 70701
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.06,
|
| 249 |
+
"learning_rate": 1.944880553316078e-05,
|
| 250 |
+
"loss": 0.8331,
|
| 251 |
+
"step": 72000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.14,
|
| 255 |
+
"learning_rate": 1.8600161242415244e-05,
|
| 256 |
+
"loss": 0.8402,
|
| 257 |
+
"step": 74000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.22,
|
| 261 |
+
"learning_rate": 1.7751516951669707e-05,
|
| 262 |
+
"loss": 0.8381,
|
| 263 |
+
"step": 76000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.31,
|
| 267 |
+
"learning_rate": 1.6902872660924173e-05,
|
| 268 |
+
"loss": 0.8362,
|
| 269 |
+
"step": 78000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.39,
|
| 273 |
+
"learning_rate": 1.605422837017864e-05,
|
| 274 |
+
"loss": 0.8318,
|
| 275 |
+
"step": 80000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.48,
|
| 279 |
+
"learning_rate": 1.5205584079433105e-05,
|
| 280 |
+
"loss": 0.835,
|
| 281 |
+
"step": 82000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.56,
|
| 285 |
+
"learning_rate": 1.4356939788687573e-05,
|
| 286 |
+
"loss": 0.8344,
|
| 287 |
+
"step": 84000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.65,
|
| 291 |
+
"learning_rate": 1.3508295497942039e-05,
|
| 292 |
+
"loss": 0.8354,
|
| 293 |
+
"step": 86000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.73,
|
| 297 |
+
"learning_rate": 1.2659651207196505e-05,
|
| 298 |
+
"loss": 0.8283,
|
| 299 |
+
"step": 88000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.82,
|
| 303 |
+
"learning_rate": 1.181100691645097e-05,
|
| 304 |
+
"loss": 0.8341,
|
| 305 |
+
"step": 90000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.9,
|
| 309 |
+
"learning_rate": 1.0962362625705435e-05,
|
| 310 |
+
"loss": 0.8225,
|
| 311 |
+
"step": 92000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.99,
|
| 315 |
+
"learning_rate": 1.0113718334959903e-05,
|
| 316 |
+
"loss": 0.8161,
|
| 317 |
+
"step": 94000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.0,
|
| 321 |
+
"eval_loss": 1.1247462034225464,
|
| 322 |
+
"eval_runtime": 285.2246,
|
| 323 |
+
"eval_samples_per_second": 50.914,
|
| 324 |
+
"step": 94268
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.07,
|
| 328 |
+
"learning_rate": 9.265074044214369e-06,
|
| 329 |
+
"loss": 0.8112,
|
| 330 |
+
"step": 96000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.16,
|
| 334 |
+
"learning_rate": 8.416429753468833e-06,
|
| 335 |
+
"loss": 0.8188,
|
| 336 |
+
"step": 98000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.24,
|
| 340 |
+
"learning_rate": 7.567785462723299e-06,
|
| 341 |
+
"loss": 0.8161,
|
| 342 |
+
"step": 100000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 4.33,
|
| 346 |
+
"learning_rate": 6.719141171977767e-06,
|
| 347 |
+
"loss": 0.8157,
|
| 348 |
+
"step": 102000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.41,
|
| 352 |
+
"learning_rate": 5.870496881232232e-06,
|
| 353 |
+
"loss": 0.8058,
|
| 354 |
+
"step": 104000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.5,
|
| 358 |
+
"learning_rate": 5.021852590486698e-06,
|
| 359 |
+
"loss": 0.8122,
|
| 360 |
+
"step": 106000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.58,
|
| 364 |
+
"learning_rate": 4.173208299741164e-06,
|
| 365 |
+
"loss": 0.8135,
|
| 366 |
+
"step": 108000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.67,
|
| 370 |
+
"learning_rate": 3.3245640089956294e-06,
|
| 371 |
+
"loss": 0.816,
|
| 372 |
+
"step": 110000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.75,
|
| 376 |
+
"learning_rate": 2.475919718250096e-06,
|
| 377 |
+
"loss": 0.8163,
|
| 378 |
+
"step": 112000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.84,
|
| 382 |
+
"learning_rate": 1.6272754275045616e-06,
|
| 383 |
+
"loss": 0.813,
|
| 384 |
+
"step": 114000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.92,
|
| 388 |
+
"learning_rate": 7.786311367590275e-07,
|
| 389 |
+
"loss": 0.8102,
|
| 390 |
+
"step": 116000
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"max_steps": 117835,
|
| 394 |
+
"num_train_epochs": 5,
|
| 395 |
+
"total_flos": 443431511673274368,
|
| 396 |
+
"trial_name": null,
|
| 397 |
+
"trial_params": null
|
| 398 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56200f69eeb801689b44b171441b8d2ba5fda94da0a48972de44aeeab294f03a
|
| 3 |
+
size 2031
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|