Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +28 -0
- events.out.tfevents.1674219058.turing.535864.0 +3 -0
- last-checkpoint/config.json +28 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +30 -0
- last-checkpoint/training_args.bin +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan20_13-50-58_turing/1674219065.6657515/events.out.tfevents.1674219065.turing.535864.2 +3 -0
- runs/Jan20_13-50-58_turing/events.out.tfevents.1674219065.turing.535864.1 +3 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-fromscratch-galician-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.25.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
events.out.tfevents.1674219058.turing.535864.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:945dc67bd2cd32d657520fe05ea3bc2c283cd8d97573cebd8848603c65e23248
|
3 |
+
size 40
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-fromscratch-galician-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.25.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baa56fc354bab9722a82d8f85c69a770342e80cba7ebb98840a157908da2ca3e
|
3 |
+
size 1270901637
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6224ac56335a66abd35ac70f16cc5cf9f099c1b47c77a2b3bfa666e0fb25f5a6
|
3 |
+
size 635440313
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02f2bb7ce981ff1e3541eb338207fdec5835069386155674aff24b7a0342a2fb
|
3 |
+
size 14575
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
|
3 |
+
size 557
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f1b26120718f1fc7514dbf4a2e75f903adca9179906a60978c2e35f5f1bfb14
|
3 |
+
size 627
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 7.173837184906006,
|
3 |
+
"best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/large/checkpoint-500",
|
4 |
+
"epoch": 0.4516201874223778,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.45,
|
12 |
+
"learning_rate": 9.698885877747666e-05,
|
13 |
+
"loss": 7.2539,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"eval_loss": 7.173837184906006,
|
19 |
+
"eval_runtime": 53.1876,
|
20 |
+
"eval_samples_per_second": 216.065,
|
21 |
+
"eval_steps_per_second": 27.018,
|
22 |
+
"step": 500
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"max_steps": 16605,
|
26 |
+
"num_train_epochs": 15,
|
27 |
+
"total_flos": 2.352130715179123e+16,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": null
|
30 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4996bd364fd243c3cfe1cd3d164ea77995538c4e1b23bef6d87942bffa66e6d
|
3 |
+
size 3515
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6224ac56335a66abd35ac70f16cc5cf9f099c1b47c77a2b3bfa666e0fb25f5a6
|
3 |
+
size 635440313
|
runs/Jan20_13-50-58_turing/1674219065.6657515/events.out.tfevents.1674219065.turing.535864.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07808dc97e7bb690acdab9d1f9c3f313b49c3c4824da3ce223a0acb87c1d1f4f
|
3 |
+
size 5621
|
runs/Jan20_13-50-58_turing/events.out.tfevents.1674219065.turing.535864.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a3e6c5ef07181261ea7ae6adbf4e7cd6906420acd9bd3e47987302b825d4d62
|
3 |
+
size 4305
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4996bd364fd243c3cfe1cd3d164ea77995538c4e1b23bef6d87942bffa66e6d
|
3 |
+
size 3515
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|