Spaces:
Running
Running
lunadebruyne
commited on
Commit
·
6de370f
1
Parent(s):
e589d46
Upload 12 files
Browse files- model/checkpoint-128/config.json +46 -0
- model/checkpoint-128/merges.txt +0 -0
- model/checkpoint-128/optimizer.pt +3 -0
- model/checkpoint-128/pytorch_model.bin +3 -0
- model/checkpoint-128/rng_state.pth +3 -0
- model/checkpoint-128/scheduler.pt +3 -0
- model/checkpoint-128/special_tokens_map.json +15 -0
- model/checkpoint-128/tokenizer.json +0 -0
- model/checkpoint-128/tokenizer_config.json +65 -0
- model/checkpoint-128/trainer_state.json +52 -0
- model/checkpoint-128/training_args.bin +3 -0
- model/checkpoint-128/vocab.json +0 -0
model/checkpoint-128/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pdelobelle/robbert-v2-dutch-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "neutral",
|
16 |
+
"1": "anger",
|
17 |
+
"2": "fear",
|
18 |
+
"3": "joy",
|
19 |
+
"4": "love",
|
20 |
+
"5": "sadness"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"anger": 1,
|
26 |
+
"fear": 2,
|
27 |
+
"joy": 3,
|
28 |
+
"love": 4,
|
29 |
+
"neutral": 0,
|
30 |
+
"sadness": 5
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"max_position_embeddings": 514,
|
34 |
+
"model_type": "roberta",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"output_past": true,
|
38 |
+
"pad_token_id": 1,
|
39 |
+
"position_embedding_type": "absolute",
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.26.0",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 40000
|
46 |
+
}
|
model/checkpoint-128/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model/checkpoint-128/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2693d54b6a9f04d61fe6004a6fedd35883ee2473059b93a01680ef098f4c01e
|
3 |
+
size 934251461
|
model/checkpoint-128/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77a5f170990c903630a02f65b3614850ee67cd42c6c87951747242be99bf5cf1
|
3 |
+
size 467140277
|
model/checkpoint-128/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1b88ea66603f645df57ae3d9172feaf0687746478ec20b7eb78bcc5056f4851
|
3 |
+
size 14575
|
model/checkpoint-128/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e03c718616c6d10fa4cacd7b3fb96e2383a923b8f06d44fb300fc8ae238e9c9
|
3 |
+
size 627
|
model/checkpoint-128/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
model/checkpoint-128/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model/checkpoint-128/tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"model_max_length": 512,
|
37 |
+
"name_or_path": "pdelobelle/robbert-v2-dutch-base",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
model/checkpoint-128/trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 128,
|
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": 0.4855,
|
13 |
+
"eval_loss": 1.3965038061141968,
|
14 |
+
"eval_runtime": 4.6299,
|
15 |
+
"eval_samples_per_second": 431.973,
|
16 |
+
"eval_steps_per_second": 6.912,
|
17 |
+
"step": 32
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.593,
|
22 |
+
"eval_loss": 1.1511962413787842,
|
23 |
+
"eval_runtime": 4.6492,
|
24 |
+
"eval_samples_per_second": 430.179,
|
25 |
+
"eval_steps_per_second": 6.883,
|
26 |
+
"step": 64
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.6645,
|
31 |
+
"eval_loss": 0.9674201607704163,
|
32 |
+
"eval_runtime": 4.6567,
|
33 |
+
"eval_samples_per_second": 429.491,
|
34 |
+
"eval_steps_per_second": 6.872,
|
35 |
+
"step": 96
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.703,
|
40 |
+
"eval_loss": 0.8914326429367065,
|
41 |
+
"eval_runtime": 4.6715,
|
42 |
+
"eval_samples_per_second": 428.129,
|
43 |
+
"eval_steps_per_second": 6.85,
|
44 |
+
"step": 128
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 128,
|
48 |
+
"num_train_epochs": 4,
|
49 |
+
"total_flos": 526241009664000.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
model/checkpoint-128/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a26ebcfe3a3774606299bb69c648781d8d092fda33c2f995bc565bd92289375
|
3 |
+
size 3451
|
model/checkpoint-128/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|