Harish Tayyar Madabushi
commited on
Commit
•
f007219
1
Parent(s):
d037687
added model
Browse files- config.json +44 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +76 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/",
|
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": 3072,
|
12 |
+
"d_model": 768,
|
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": 12,
|
22 |
+
"n_layer": 12,
|
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": "4.10.0.dev0",
|
40 |
+
"untie_r": true,
|
41 |
+
"use_mems_eval": true,
|
42 |
+
"use_mems_train": false,
|
43 |
+
"vocab_size": 32000
|
44 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be8c9ff336c35797bc25e0eef3fd24fc4f05dd398692307c8349ab79d9b886fb
|
3 |
+
size 938605248
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f201b659e3318566a393aba180d68d31a37cc608c352c4b677c751fd79f5cf40
|
3 |
+
size 469320109
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5f4cfdd3ab0a53477380dbf33d4d6ded435eb7a8a95682ae6285864405701e4
|
3 |
+
size 14583
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50c51c41af26ac9acacfe0d4f6670ca36ab4130fac2559e6ab82c119c1eba619
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
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": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/", "tokenizer_class": "XLNetTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7553438835970898,
|
3 |
+
"best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/FalseFalse-0/train_from_dev_and_test_short.csv/0/checkpoint-15",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 15,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.7596566677093506,
|
13 |
+
"eval_f1": 0.7480546061905038,
|
14 |
+
"eval_f1_binary": 0.8021201413427562,
|
15 |
+
"eval_f1_weighted": 0.7598886932839152,
|
16 |
+
"eval_loss": 0.6537606716156006,
|
17 |
+
"eval_runtime": 1.8405,
|
18 |
+
"eval_samples_per_second": 253.19,
|
19 |
+
"eval_steps_per_second": 32.056,
|
20 |
+
"step": 3
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.7231759428977966,
|
25 |
+
"eval_f1": 0.677726490502919,
|
26 |
+
"eval_f1_binary": 0.7987519500780031,
|
27 |
+
"eval_f1_weighted": 0.7042170417403839,
|
28 |
+
"eval_loss": 0.7053621411323547,
|
29 |
+
"eval_runtime": 1.8333,
|
30 |
+
"eval_samples_per_second": 254.191,
|
31 |
+
"eval_steps_per_second": 32.183,
|
32 |
+
"step": 6
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.7145922780036926,
|
37 |
+
"eval_f1": 0.6427266176682519,
|
38 |
+
"eval_f1_binary": 0.802962962962963,
|
39 |
+
"eval_f1_weighted": 0.6777998091276093,
|
40 |
+
"eval_loss": 0.9234773516654968,
|
41 |
+
"eval_runtime": 1.8337,
|
42 |
+
"eval_samples_per_second": 254.13,
|
43 |
+
"eval_steps_per_second": 32.175,
|
44 |
+
"step": 9
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.0,
|
48 |
+
"eval_accuracy": 0.7446351647377014,
|
49 |
+
"eval_f1": 0.7080308111893266,
|
50 |
+
"eval_f1_binary": 0.8114104595879557,
|
51 |
+
"eval_f1_weighted": 0.7306589745727177,
|
52 |
+
"eval_loss": 0.655060887336731,
|
53 |
+
"eval_runtime": 1.835,
|
54 |
+
"eval_samples_per_second": 253.945,
|
55 |
+
"eval_steps_per_second": 32.152,
|
56 |
+
"step": 12
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.774678111076355,
|
61 |
+
"eval_f1": 0.7553438835970898,
|
62 |
+
"eval_f1_binary": 0.8241206030150753,
|
63 |
+
"eval_f1_weighted": 0.7703980153151897,
|
64 |
+
"eval_loss": 0.61130690574646,
|
65 |
+
"eval_runtime": 1.8335,
|
66 |
+
"eval_samples_per_second": 254.158,
|
67 |
+
"eval_steps_per_second": 32.179,
|
68 |
+
"step": 15
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"max_steps": 27,
|
72 |
+
"num_train_epochs": 9,
|
73 |
+
"total_flos": 30980730401280.0,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91299a58c260af6a5bb783059eabd6c254f03534431fda5e1fbebb30535bf95e
|
3 |
+
size 2799
|