Ubuntu
commited on
Commit
•
39794fc
1
Parent(s):
33786b9
initial upload
Browse files- all_results.json +14 -0
- config.json +28 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +67 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.963302752293578,
|
4 |
+
"eval_loss": 0.19932273030281067,
|
5 |
+
"eval_runtime": 4.0116,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 217.369,
|
8 |
+
"eval_steps_per_second": 3.49,
|
9 |
+
"train_loss": 0.0722438246860803,
|
10 |
+
"train_runtime": 2878.5938,
|
11 |
+
"train_samples": 67349,
|
12 |
+
"train_samples_per_second": 233.965,
|
13 |
+
"train_steps_per_second": 1.219
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "sst2",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"transformers_version": "4.7.0.dev0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.963302752293578,
|
4 |
+
"eval_loss": 0.19932273030281067,
|
5 |
+
"eval_runtime": 4.0116,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 217.369,
|
8 |
+
"eval_steps_per_second": 3.49
|
9 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4d88706b392af51877b02f892487f392fd19dd386f9ec03969fd12aadae17bf
|
3 |
+
size 1421616723
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.0722438246860803,
|
4 |
+
"train_runtime": 2878.5938,
|
5 |
+
"train_samples": 67349,
|
6 |
+
"train_samples_per_second": 233.965,
|
7 |
+
"train_steps_per_second": 1.219
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 3510,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.42,
|
12 |
+
"learning_rate": 1.7150997150997152e-05,
|
13 |
+
"loss": 0.2235,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.85,
|
18 |
+
"learning_rate": 1.4301994301994305e-05,
|
19 |
+
"loss": 0.1031,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 4.27,
|
24 |
+
"learning_rate": 1.1452991452991454e-05,
|
25 |
+
"loss": 0.0651,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 5.7,
|
30 |
+
"learning_rate": 8.603988603988605e-06,
|
31 |
+
"loss": 0.0455,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 7.12,
|
36 |
+
"learning_rate": 5.7549857549857555e-06,
|
37 |
+
"loss": 0.0321,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 8.55,
|
42 |
+
"learning_rate": 2.9059829059829063e-06,
|
43 |
+
"loss": 0.0216,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 9.97,
|
48 |
+
"learning_rate": 5.6980056980056986e-08,
|
49 |
+
"loss": 0.0158,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 10.0,
|
54 |
+
"step": 3510,
|
55 |
+
"total_flos": 1.8380744804433408e+17,
|
56 |
+
"train_loss": 0.0722438246860803,
|
57 |
+
"train_runtime": 2878.5938,
|
58 |
+
"train_samples_per_second": 233.965,
|
59 |
+
"train_steps_per_second": 1.219
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"max_steps": 3510,
|
63 |
+
"num_train_epochs": 10,
|
64 |
+
"total_flos": 1.8380744804433408e+17,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d99dbd5ada36e0fe8bb088f808e8972a18d84780df62abc447984324ec3bc64
|
3 |
+
size 2479
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|