marcopost-it
commited on
Commit
•
1dcec44
1
Parent(s):
4a2b23f
first model
Browse files- all_results.json +14 -0
- config.json +23 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 1294196736,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 420376576,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 441293312,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 17265926144,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 799649792,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1320941056,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 7582508544,
|
| 11 |
+
"train_runtime": 388027.9373,
|
| 12 |
+
"train_samples": 15140037,
|
| 13 |
+
"train_samples_per_second": 1.829
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"gradient_checkpointing": false,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"transformers_version": "4.5.1",
|
| 20 |
+
"type_vocab_size": 2,
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 31102
|
| 23 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77abf7cf625bbd4b0ca09c68391e00228919a69fc9eb0e32e1dc00d71c41ee11
|
| 3 |
+
size 439931410
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/bert-base-italian-xxl-cased", "do_basic_tokenize": true, "never_split": null}
|
train_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 1294196736,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 420376576,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 441293312,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 17265926144,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 799649792,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1320941056,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 7582508544,
|
| 11 |
+
"train_runtime": 388027.9373,
|
| 12 |
+
"train_samples": 15140037,
|
| 13 |
+
"train_samples_per_second": 1.829
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cc8dbff88247bad412561640a8c257361cb1ab066cda2b41ad180d6bc7c18e
|
| 3 |
+
size 2351
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|