EhsanAghazadeh commited on
Commit
cef209f
1 Parent(s): 07f1c03

Initial commit

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "cola",
18
+ "initializer_range": 0.02,
19
+ "layer_norm_eps": 1e-12,
20
+ "mem_len": null,
21
+ "model_type": "xlnet",
22
+ "n_head": 16,
23
+ "n_layer": 24,
24
+ "pad_token_id": 5,
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
+ "transformers_version": "4.5.1",
39
+ "untie_r": true,
40
+ "use_mems_eval": true,
41
+ "use_mems_train": false,
42
+ "vocab_size": 32000
43
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88b12c618f24cb45a783885b20aa1b0bf676e916d590834611809e30def4f2a
3
+ size 2890816569
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8838583dc1cf638e3424fbe26f5c4fe76fdd4afba8389d76b88b1d31bcce8284
3
+ size 1445440509
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336e7949185e7af155a9112e2b39d9ac33ba331d694e455234c4743086aef688
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<eop>", "<eod>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "xlnet-large-cased"}
trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.8709073900841908,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.47,
12
+ "learning_rate": 4.4153414405986905e-05,
13
+ "loss": 0.6437,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.94,
18
+ "learning_rate": 3.8306828811973814e-05,
19
+ "loss": 0.6233,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.4,
24
+ "learning_rate": 3.246024321796071e-05,
25
+ "loss": 0.6296,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.87,
30
+ "learning_rate": 2.6613657623947615e-05,
31
+ "loss": 0.6285,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 4276,
36
+ "num_train_epochs": 4,
37
+ "total_flos": 4439628195494400.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e62e34df944aa90b2bbc0df5665e61e488891c160d044d82d294a3c70b9a07
3
+ size 2351