Upload 7 files
Browse files- config.json +32 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +52 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "m-polignano-uniba/bert_uncased_L-12_H-768_A-12_italian_alb3rt0",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 128000
|
32 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51a90be619d82cbdbab2ad60bf959b69851165cf080ca7f6f9f641fd8f04f8c1
|
3 |
+
size 1474893434
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3beb68f40d4a84c287feebf7cadf43e99ce9bebd7fdfdb26210e8102062ec1c
|
3 |
+
size 737460786
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45e0f913b3e9d371afc0779295dadf1ea7f5dc9b77206352b6c13df52fb6abad
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a7b7c01854588932ef109a93fc6c82a8dae98b947f34455716c77d82ef89a6f
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0010390824172645807,
|
3 |
+
"best_model_checkpoint": "./model_stereotype/checkpoint-544",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 544,
|
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 |
+
"learning_rate": 1.866666666666667e-05,
|
13 |
+
"loss": 0.0021,
|
14 |
+
"step": 272
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7658022690437601,
|
19 |
+
"eval_f1": 0.7756211180124224,
|
20 |
+
"eval_loss": 0.0014655768172815442,
|
21 |
+
"eval_precision": 0.7444113263785395,
|
22 |
+
"eval_recall": 0.8095623987034035,
|
23 |
+
"eval_runtime": 7.495,
|
24 |
+
"eval_samples_per_second": 658.575,
|
25 |
+
"eval_steps_per_second": 41.228,
|
26 |
+
"step": 272
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"learning_rate": 1.7333333333333336e-05,
|
31 |
+
"loss": 0.0007,
|
32 |
+
"step": 544
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7862641815235009,
|
37 |
+
"eval_f1": 0.7903001391373485,
|
38 |
+
"eval_loss": 0.0010390824172645807,
|
39 |
+
"eval_precision": 0.7756535310183379,
|
40 |
+
"eval_recall": 0.8055105348460292,
|
41 |
+
"eval_runtime": 7.5689,
|
42 |
+
"eval_samples_per_second": 652.141,
|
43 |
+
"eval_steps_per_second": 40.825,
|
44 |
+
"step": 544
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 4080,
|
48 |
+
"num_train_epochs": 15,
|
49 |
+
"total_flos": 446877683088000.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b5c90ffde318fc5196aa0690a4ae50d4444d8a73baa866dca7bc0c902b1d3a8
|
3 |
+
size 4344
|