Commit
•
b31ccfd
1
Parent(s):
a113eae
Training in progress, epoch 1
Browse files- checkpoint-20000/config.json +44 -0
- checkpoint-20000/optimizer.pt +3 -0
- checkpoint-20000/pytorch_model.bin +3 -0
- checkpoint-20000/rng_state.pth +3 -0
- checkpoint-20000/scheduler.pt +3 -0
- checkpoint-20000/special_tokens_map.json +19 -0
- checkpoint-20000/spiece.model +3 -0
- checkpoint-20000/tokenizer.json +0 -0
- checkpoint-20000/tokenizer_config.json +26 -0
- checkpoint-20000/trainer_state.json +266 -0
- checkpoint-20000/training_args.bin +3 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- runs/Feb17_12-13-22_faa0f5d18b18/1676636015.188479/events.out.tfevents.1676636015.faa0f5d18b18.23.1 +3 -0
- runs/Feb17_12-13-22_faa0f5d18b18/events.out.tfevents.1676636015.faa0f5d18b18.23.0 +3 -0
- special_tokens_map.json +19 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +26 -0
- training_args.bin +3 -0
checkpoint-20000/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlnet-large-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attn_type": "bi",
|
| 7 |
+
"bi_data": false,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"clamp_len": -1,
|
| 10 |
+
"d_head": 64,
|
| 11 |
+
"d_inner": 4096,
|
| 12 |
+
"d_model": 1024,
|
| 13 |
+
"dropout": 0.1,
|
| 14 |
+
"end_n_top": 5,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"ff_activation": "gelu",
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"mem_len": null,
|
| 20 |
+
"model_type": "xlnet",
|
| 21 |
+
"n_head": 16,
|
| 22 |
+
"n_layer": 24,
|
| 23 |
+
"pad_token_id": 5,
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"reuse_len": null,
|
| 26 |
+
"same_length": false,
|
| 27 |
+
"start_n_top": 5,
|
| 28 |
+
"summary_activation": "tanh",
|
| 29 |
+
"summary_last_dropout": 0.1,
|
| 30 |
+
"summary_type": "last",
|
| 31 |
+
"summary_use_proj": true,
|
| 32 |
+
"task_specific_params": {
|
| 33 |
+
"text-generation": {
|
| 34 |
+
"do_sample": true,
|
| 35 |
+
"max_length": 250
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.20.1",
|
| 40 |
+
"untie_r": true,
|
| 41 |
+
"use_mems_eval": true,
|
| 42 |
+
"use_mems_train": false,
|
| 43 |
+
"vocab_size": 32000
|
| 44 |
+
}
|
checkpoint-20000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84117b05b875cc9ae07f175f992d8b3cd8252185c39020409a6f35b6cb4b3ac0
|
| 3 |
+
size 2890797581
|
checkpoint-20000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a3083ee78196dc9ea98c156bebe094884825aa646fbf1350006a05cd78e816
|
| 3 |
+
size 1445417157
|
checkpoint-20000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd3c7e4a0a9e84eef07763f07c642df91d38198e3850f01f51e54d5a55cf6f3
|
| 3 |
+
size 14503
|
checkpoint-20000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de9fddf8d3fd2ab427b34df618bafd9cd2fad5b2ebffedc1cafb2f13790e2720
|
| 3 |
+
size 623
|
checkpoint-20000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<eop>",
|
| 4 |
+
"<eod>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<cls>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "<sep>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
checkpoint-20000/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
| 3 |
+
size 798011
|
checkpoint-20000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-20000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<eop>",
|
| 4 |
+
"<eod>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<cls>",
|
| 8 |
+
"do_lower_case": false,
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"keep_accents": false,
|
| 11 |
+
"mask_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<mask>",
|
| 14 |
+
"lstrip": true,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"name_or_path": "xlnet-large-cased",
|
| 20 |
+
"pad_token": "<pad>",
|
| 21 |
+
"remove_space": true,
|
| 22 |
+
"sep_token": "<sep>",
|
| 23 |
+
"special_tokens_map_file": null,
|
| 24 |
+
"tokenizer_class": "XLNetTokenizer",
|
| 25 |
+
"unk_token": "<unk>"
|
| 26 |
+
}
|
checkpoint-20000/trainer_state.json
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7702265372168284,
|
| 3 |
+
"best_model_checkpoint": "amazon-xlnet-large-2/checkpoint-20000",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 20000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 9.75e-06,
|
| 13 |
+
"loss": 0.7155,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 9.5e-06,
|
| 19 |
+
"loss": 0.6416,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 9.250000000000001e-06,
|
| 25 |
+
"loss": 0.6013,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 9e-06,
|
| 31 |
+
"loss": 0.6026,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 8.750000000000001e-06,
|
| 37 |
+
"loss": 0.5762,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 8.5e-06,
|
| 43 |
+
"loss": 0.6114,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 8.25e-06,
|
| 49 |
+
"loss": 0.6004,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 8.000000000000001e-06,
|
| 55 |
+
"loss": 0.5701,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 7.75e-06,
|
| 61 |
+
"loss": 0.6027,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 7.500000000000001e-06,
|
| 67 |
+
"loss": 0.568,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.28,
|
| 72 |
+
"learning_rate": 7.25e-06,
|
| 73 |
+
"loss": 0.5704,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3,
|
| 78 |
+
"learning_rate": 7e-06,
|
| 79 |
+
"loss": 0.5688,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33,
|
| 84 |
+
"learning_rate": 6.750000000000001e-06,
|
| 85 |
+
"loss": 0.5657,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35,
|
| 90 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 91 |
+
"loss": 0.5517,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 6.25e-06,
|
| 97 |
+
"loss": 0.577,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"learning_rate": 6e-06,
|
| 103 |
+
"loss": 0.5462,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.42,
|
| 108 |
+
"learning_rate": 5.75e-06,
|
| 109 |
+
"loss": 0.576,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.45,
|
| 114 |
+
"learning_rate": 5.500000000000001e-06,
|
| 115 |
+
"loss": 0.5602,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.47,
|
| 120 |
+
"learning_rate": 5.2500000000000006e-06,
|
| 121 |
+
"loss": 0.5697,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5501,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.53,
|
| 132 |
+
"learning_rate": 4.75e-06,
|
| 133 |
+
"loss": 0.5489,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 4.5e-06,
|
| 139 |
+
"loss": 0.5818,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.57,
|
| 144 |
+
"learning_rate": 4.25e-06,
|
| 145 |
+
"loss": 0.5433,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6,
|
| 150 |
+
"learning_rate": 4.000000000000001e-06,
|
| 151 |
+
"loss": 0.5318,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.62,
|
| 156 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 157 |
+
"loss": 0.5762,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.65,
|
| 162 |
+
"learning_rate": 3.5e-06,
|
| 163 |
+
"loss": 0.5335,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.68,
|
| 168 |
+
"learning_rate": 3.2500000000000002e-06,
|
| 169 |
+
"loss": 0.5483,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7,
|
| 174 |
+
"learning_rate": 3e-06,
|
| 175 |
+
"loss": 0.537,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.72,
|
| 180 |
+
"learning_rate": 2.7500000000000004e-06,
|
| 181 |
+
"loss": 0.5403,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.75,
|
| 186 |
+
"learning_rate": 2.5e-06,
|
| 187 |
+
"loss": 0.5545,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.78,
|
| 192 |
+
"learning_rate": 2.25e-06,
|
| 193 |
+
"loss": 0.526,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.8,
|
| 198 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 199 |
+
"loss": 0.5623,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.82,
|
| 204 |
+
"learning_rate": 1.75e-06,
|
| 205 |
+
"loss": 0.5331,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.85,
|
| 210 |
+
"learning_rate": 1.5e-06,
|
| 211 |
+
"loss": 0.5757,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.88,
|
| 216 |
+
"learning_rate": 1.25e-06,
|
| 217 |
+
"loss": 0.568,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.9,
|
| 222 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 223 |
+
"loss": 0.5492,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.93,
|
| 228 |
+
"learning_rate": 7.5e-07,
|
| 229 |
+
"loss": 0.5629,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.95,
|
| 234 |
+
"learning_rate": 5.000000000000001e-07,
|
| 235 |
+
"loss": 0.5445,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.97,
|
| 240 |
+
"learning_rate": 2.5000000000000004e-07,
|
| 241 |
+
"loss": 0.5629,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.0,
|
| 246 |
+
"learning_rate": 0.0,
|
| 247 |
+
"loss": 0.5505,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0,
|
| 252 |
+
"eval_accuracy": 0.77635,
|
| 253 |
+
"eval_f1": 0.7702265372168284,
|
| 254 |
+
"eval_loss": 0.5627002716064453,
|
| 255 |
+
"eval_runtime": 539.3763,
|
| 256 |
+
"eval_samples_per_second": 37.08,
|
| 257 |
+
"eval_steps_per_second": 9.27,
|
| 258 |
+
"step": 20000
|
| 259 |
+
}
|
| 260 |
+
],
|
| 261 |
+
"max_steps": 20000,
|
| 262 |
+
"num_train_epochs": 1,
|
| 263 |
+
"total_flos": 2.62860464073984e+16,
|
| 264 |
+
"trial_name": null,
|
| 265 |
+
"trial_params": null
|
| 266 |
+
}
|
checkpoint-20000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1caabba21deb376718ba50826d299a3aa8e9ea8e17c866daa5c86fcb35942668
|
| 3 |
+
size 3375
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlnet-large-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attn_type": "bi",
|
| 7 |
+
"bi_data": false,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"clamp_len": -1,
|
| 10 |
+
"d_head": 64,
|
| 11 |
+
"d_inner": 4096,
|
| 12 |
+
"d_model": 1024,
|
| 13 |
+
"dropout": 0.1,
|
| 14 |
+
"end_n_top": 5,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"ff_activation": "gelu",
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"mem_len": null,
|
| 20 |
+
"model_type": "xlnet",
|
| 21 |
+
"n_head": 16,
|
| 22 |
+
"n_layer": 24,
|
| 23 |
+
"pad_token_id": 5,
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"reuse_len": null,
|
| 26 |
+
"same_length": false,
|
| 27 |
+
"start_n_top": 5,
|
| 28 |
+
"summary_activation": "tanh",
|
| 29 |
+
"summary_last_dropout": 0.1,
|
| 30 |
+
"summary_type": "last",
|
| 31 |
+
"summary_use_proj": true,
|
| 32 |
+
"task_specific_params": {
|
| 33 |
+
"text-generation": {
|
| 34 |
+
"do_sample": true,
|
| 35 |
+
"max_length": 250
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.20.1",
|
| 40 |
+
"untie_r": true,
|
| 41 |
+
"use_mems_eval": true,
|
| 42 |
+
"use_mems_train": false,
|
| 43 |
+
"vocab_size": 32000
|
| 44 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a3083ee78196dc9ea98c156bebe094884825aa646fbf1350006a05cd78e816
|
| 3 |
+
size 1445417157
|
runs/Feb17_12-13-22_faa0f5d18b18/1676636015.188479/events.out.tfevents.1676636015.faa0f5d18b18.23.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc68be33e396f06b6bd39528c631fb6c108ada0e50deffb6876391513528b011
|
| 3 |
+
size 5347
|
runs/Feb17_12-13-22_faa0f5d18b18/events.out.tfevents.1676636015.faa0f5d18b18.23.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae8672ca8fb5d6274b18f607ed1838f884df7534fa0b4d1ead2181e5fb9099c4
|
| 3 |
+
size 10552
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<eop>",
|
| 4 |
+
"<eod>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<cls>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "<sep>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
| 3 |
+
size 798011
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<eop>",
|
| 4 |
+
"<eod>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<cls>",
|
| 8 |
+
"do_lower_case": false,
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"keep_accents": false,
|
| 11 |
+
"mask_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<mask>",
|
| 14 |
+
"lstrip": true,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"name_or_path": "xlnet-large-cased",
|
| 20 |
+
"pad_token": "<pad>",
|
| 21 |
+
"remove_space": true,
|
| 22 |
+
"sep_token": "<sep>",
|
| 23 |
+
"special_tokens_map_file": null,
|
| 24 |
+
"tokenizer_class": "XLNetTokenizer",
|
| 25 |
+
"unk_token": "<unk>"
|
| 26 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1caabba21deb376718ba50826d299a3aa8e9ea8e17c866daa5c86fcb35942668
|
| 3 |
+
size 3375
|