StevenLimcorn
commited on
Commit
·
8dd1579
1
Parent(s):
061a8cf
Upload 10 files
Browse files- config.json +3 -4
- merges.txt +0 -0
- optimizer.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/content/
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
@@ -20,8 +19,8 @@
|
|
20 |
"num_hidden_layers": 24,
|
21 |
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
-
"transformers_version": "4.
|
24 |
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 50265
|
27 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/result/unsup-simcse-roberta-large-semeval2015-laptops",
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
8 |
"eos_token_id": 2,
|
9 |
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
|
|
19 |
"num_hidden_layers": 24,
|
20 |
"pad_token_id": 1,
|
21 |
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.2.1",
|
23 |
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 50265
|
26 |
+
}
|
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:a08e8d24b6b05d85181c3c42a45ea5082e86d8c5fa495f1c6c00c9494d55cbf4
|
3 |
+
size 2843107653
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:398715dab04d46eb5cc5b3486dc92fcc644db09519638e7f2a720744d2f90f43
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "princeton-nlp/unsup-simcse-roberta-large", "special_tokens_map_file": "/root/.cache/huggingface/transformers/6d59ec8e128c32fbf5663dad4484f60104c7f3b2520047fbaf57bc63b260e0fd.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342"}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 30.0
|
2 |
+
train_runtime = 1610.2853
|
3 |
+
train_samples_per_second = 0.522
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.828283390419402,
|
3 |
+
"best_model_checkpoint": "/content/result/unsup-simcse-roberta-large-semeval2015-laptops",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 840,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.46,
|
12 |
+
"eval_avg_sts": 0.7866241458854294,
|
13 |
+
"eval_sickr_spearman": 0.7525337179492227,
|
14 |
+
"eval_stsb_spearman": 0.820714573821636,
|
15 |
+
"step": 125
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 8.93,
|
19 |
+
"eval_avg_sts": 0.7755652925596941,
|
20 |
+
"eval_sickr_spearman": 0.7325310696931179,
|
21 |
+
"eval_stsb_spearman": 0.8185995154262702,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 13.39,
|
26 |
+
"eval_avg_sts": 0.7783432375652614,
|
27 |
+
"eval_sickr_spearman": 0.7284030847111207,
|
28 |
+
"eval_stsb_spearman": 0.828283390419402,
|
29 |
+
"step": 375
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 17.86,
|
33 |
+
"learning_rate": 2.023809523809524e-05,
|
34 |
+
"loss": 0.0015,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 17.86,
|
39 |
+
"eval_avg_sts": 0.7641535833191572,
|
40 |
+
"eval_sickr_spearman": 0.7357065979335973,
|
41 |
+
"eval_stsb_spearman": 0.7926005687047171,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 22.32,
|
46 |
+
"eval_avg_sts": 0.7692839856507644,
|
47 |
+
"eval_sickr_spearman": 0.7284775809494513,
|
48 |
+
"eval_stsb_spearman": 0.8100903903520775,
|
49 |
+
"step": 625
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 26.79,
|
53 |
+
"eval_avg_sts": 0.7722064928209667,
|
54 |
+
"eval_sickr_spearman": 0.7298525192592187,
|
55 |
+
"eval_stsb_spearman": 0.8145604663827146,
|
56 |
+
"step": 750
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 30.0,
|
60 |
+
"step": 840,
|
61 |
+
"train_runtime": 1610.2853,
|
62 |
+
"train_samples_per_second": 0.522
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 840,
|
66 |
+
"num_train_epochs": 30,
|
67 |
+
"total_flos": 7117989287583744,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b16f7b943969315982e43c1e3e7da4ea3b3e5f64c817e9daeaa346f77bbae13
|
3 |
+
size 2107
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|