edumunozsala
commited on
Commit
•
0d59578
1
Parent(s):
97737b2
commit files to HF hub
Browse files- checkpoint-1329/config.json +29 -0
- checkpoint-1329/merges.txt +0 -0
- checkpoint-1329/optimizer.pt +3 -0
- checkpoint-1329/pytorch_model.bin +3 -0
- checkpoint-1329/rng_state.pth +3 -0
- checkpoint-1329/scaler.pt +3 -0
- checkpoint-1329/scheduler.pt +3 -0
- checkpoint-1329/special_tokens_map.json +1 -0
- checkpoint-1329/tokenizer.json +0 -0
- checkpoint-1329/tokenizer_config.json +1 -0
- checkpoint-1329/trainer_state.json +50 -0
- checkpoint-1329/training_args.bin +3 -0
- checkpoint-1329/vocab.json +0 -0
- config.json +29 -0
- merges.txt +0 -0
- output.tar.gz +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-1329/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/RuPERTa-base",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"transformers_version": "4.6.1",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 52000
|
29 |
+
}
|
checkpoint-1329/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1329/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85426e7cccc1989fd380a398746c807cf7e309e5c510c512d75c80327edece25
|
3 |
+
size 1007963345
|
checkpoint-1329/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc05a9ad531de2438300efe50279758c1d5c2801d08fc85f2c57b9032847fd3
|
3 |
+
size 504009161
|
checkpoint-1329/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79caf4b4d1ffafd1c1bdf54d218dd1db1cb7ff816574a3804cf02f9bd1a7cb0a
|
3 |
+
size 14657
|
checkpoint-1329/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0991f03871b8ca058cbfc8112957ccab3725257cd85d7a12251165521e2d9b60
|
3 |
+
size 559
|
checkpoint-1329/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0f9610481fadeea44390444cb542baa4c3cd3e3b19c04409d4b9e7b62e2e388
|
3 |
+
size 623
|
checkpoint-1329/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}}
|
checkpoint-1329/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1329/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"}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/199ac15ad8f31a9c691ee1721f77e5417428fe4cb8a0d06e3aa5bf2167a4cf2c.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "mrm8488/RuPERTa-base"}
|
checkpoint-1329/trainer_state.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3160930573940277,
|
3 |
+
"best_model_checkpoint": "/opt/ml/model/checkpoint-1329",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 1329,
|
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": 0.7650666666666667,
|
13 |
+
"eval_f1": 0.7940144961421556,
|
14 |
+
"eval_loss": 0.48894673585891724,
|
15 |
+
"eval_precision": 0.7039800995024875,
|
16 |
+
"eval_recall": 0.910455764075067,
|
17 |
+
"eval_runtime": 114.6163,
|
18 |
+
"eval_samples_per_second": 32.718,
|
19 |
+
"step": 391
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 0.38,
|
23 |
+
"learning_rate": 2.994e-05,
|
24 |
+
"loss": 0.4577,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.75,
|
29 |
+
"learning_rate": 1.1942098914354645e-05,
|
30 |
+
"loss": 0.3945,
|
31 |
+
"step": 1000
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 1.0,
|
35 |
+
"eval_accuracy": 0.8629333333333333,
|
36 |
+
"eval_f1": 0.8648790746582545,
|
37 |
+
"eval_loss": 0.3160930573940277,
|
38 |
+
"eval_precision": 0.8479381443298969,
|
39 |
+
"eval_recall": 0.8825107296137339,
|
40 |
+
"eval_runtime": 114.2725,
|
41 |
+
"eval_samples_per_second": 32.816,
|
42 |
+
"step": 1329
|
43 |
+
}
|
44 |
+
],
|
45 |
+
"max_steps": 1329,
|
46 |
+
"num_train_epochs": 1,
|
47 |
+
"total_flos": 5802820215091200.0,
|
48 |
+
"trial_name": null,
|
49 |
+
"trial_params": null
|
50 |
+
}
|
checkpoint-1329/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96e4499e3d195f280a9a2fb6cc2e06b1146519df2f974d078adb55855aec71a
|
3 |
+
size 2415
|
checkpoint-1329/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/RuPERTa-base",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"transformers_version": "4.6.1",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 52000
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output.tar.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe99e23333d3d941623c20794e4ff3c4d5299dfe30477348551bea85e8771f1
|
3 |
+
size 302
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc05a9ad531de2438300efe50279758c1d5c2801d08fc85f2c57b9032847fd3
|
3 |
+
size 504009161
|
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": {"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"}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/199ac15ad8f31a9c691ee1721f77e5417428fe4cb8a0d06e3aa5bf2167a4cf2c.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "mrm8488/RuPERTa-base"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96e4499e3d195f280a9a2fb6cc2e06b1146519df2f974d078adb55855aec71a
|
3 |
+
size 2415
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|