Upload 7 files
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +61 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ivamarinova/bg-news-bert/",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"problem_type": "single_label_classification",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.22.0.dev0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30001
|
26 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:619ab3e1b11ed3da6529a1270c5866be2b19dcee5187655a96dfa2e38e6225f9
|
3 |
+
size 872785501
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c2a50dd418f5b9e972e7409bda985223c069a48cd420182c780e08693ac400d
|
3 |
+
size 436405613
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734154c80cf75df4e04111b7c0979049d0d2684e2ba4a78d65036d495b32c261
|
3 |
+
size 15523
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edc5ed94e55d078b74bd65b5417f9847e4027b2ed414c0718b5dbaa5c5c5cf66
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 235,
|
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": 0.75,
|
13 |
+
"eval_loss": 0.5727023482322693,
|
14 |
+
"eval_runtime": 1.0164,
|
15 |
+
"eval_samples_per_second": 106.257,
|
16 |
+
"eval_steps_per_second": 6.887,
|
17 |
+
"step": 47
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.7962962962962963,
|
22 |
+
"eval_loss": 0.5028897523880005,
|
23 |
+
"eval_runtime": 1.0142,
|
24 |
+
"eval_samples_per_second": 106.487,
|
25 |
+
"eval_steps_per_second": 6.902,
|
26 |
+
"step": 94
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.8240740740740741,
|
31 |
+
"eval_loss": 0.7567664980888367,
|
32 |
+
"eval_runtime": 1.019,
|
33 |
+
"eval_samples_per_second": 105.991,
|
34 |
+
"eval_steps_per_second": 6.87,
|
35 |
+
"step": 141
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.8148148148148148,
|
40 |
+
"eval_loss": 0.8691176176071167,
|
41 |
+
"eval_runtime": 1.0115,
|
42 |
+
"eval_samples_per_second": 106.777,
|
43 |
+
"eval_steps_per_second": 6.921,
|
44 |
+
"step": 188
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.8148148148148148,
|
49 |
+
"eval_loss": 0.9419552683830261,
|
50 |
+
"eval_runtime": 1.0218,
|
51 |
+
"eval_samples_per_second": 105.692,
|
52 |
+
"eval_steps_per_second": 6.85,
|
53 |
+
"step": 235
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 235,
|
57 |
+
"num_train_epochs": 5,
|
58 |
+
"total_flos": 986666457600000.0,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ea60b1cbc7357b60149b0f9d1245761908f4e4a602bb54616023481a3db919e
|
3 |
+
size 3439
|