Upload 11 files
Browse files- config.json +5 -5
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +2 -2
- trainer_state.json +25 -0
- training_args.bin +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "deepset/xlm-roberta-
|
3 |
"architectures": [
|
4 |
"XLMRobertaForQuestionAnswering"
|
5 |
],
|
@@ -10,16 +10,16 @@
|
|
10 |
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
-
"hidden_size":
|
14 |
"initializer_range": 0.02,
|
15 |
-
"intermediate_size":
|
16 |
"language": "english",
|
17 |
"layer_norm_eps": 1e-05,
|
18 |
"max_position_embeddings": 514,
|
19 |
"model_type": "xlm-roberta",
|
20 |
"name": "XLMRoberta",
|
21 |
-
"num_attention_heads":
|
22 |
-
"num_hidden_layers":
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 1,
|
25 |
"position_embedding_type": "absolute",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "deepset/xlm-roberta-base-squad2",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForQuestionAnswering"
|
5 |
],
|
|
|
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 |
"language": "english",
|
17 |
"layer_norm_eps": 1e-05,
|
18 |
"max_position_embeddings": 514,
|
19 |
"model_type": "xlm-roberta",
|
20 |
"name": "XLMRoberta",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 1,
|
25 |
"position_embedding_type": "absolute",
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c1c3dbdcff612e7464cf5ae414558dc454324edb0c4e73420511978e11942e
|
3 |
+
size 2219797189
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc8c652ef5cfc839167fb8e43757cfdff727f6046499b379981d74faaaba4242
|
3 |
+
size 1109883945
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:556647febb788da6dd49a88a8ed603748321637cc7055b1bb12850e2d4f60da4
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a870f21458d323a03674433a89db03696c1277d8f9575a76e764158222f7d4e
|
3 |
+
size 627
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:167066c03829058ec15ff5404e54585316251e89eec3f758bced173717de5322
|
3 |
+
size 17098346
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6045949214026602,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6,
|
13 |
+
"learning_rate": 2.0931076178960096e-05,
|
14 |
+
"loss": 2.1458,
|
15 |
+
"step": 500
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"logging_steps": 500,
|
19 |
+
"max_steps": 1654,
|
20 |
+
"num_train_epochs": 2,
|
21 |
+
"save_steps": 500,
|
22 |
+
"total_flos": 1175835405312000.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0396ee3d2be92358cee6e6bb521dc2761d5ef3dab0ef6d880752470f3795821
|
3 |
+
size 4027
|