Model save
Browse files- last-checkpoint/config.json +0 -27
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -15
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -17
- last-checkpoint/trainer_state.json +0 -72
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
- runs/Feb05_19-18-25_turing/events.out.tfevents.1675621116.turing.942264.1 +2 -2
last-checkpoint/config.json
DELETED
@@ -1,27 +0,0 @@
|
|
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 |
-
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size": 768,
|
13 |
-
"initializer_range": 0.02,
|
14 |
-
"intermediate_size": 3072,
|
15 |
-
"layer_norm_eps": 1e-05,
|
16 |
-
"max_position_embeddings": 514,
|
17 |
-
"model_type": "roberta",
|
18 |
-
"num_attention_heads": 12,
|
19 |
-
"num_hidden_layers": 12,
|
20 |
-
"pad_token_id": 1,
|
21 |
-
"position_embedding_type": "absolute",
|
22 |
-
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.24.0",
|
24 |
-
"type_vocab_size": 1,
|
25 |
-
"use_cache": true,
|
26 |
-
"vocab_size": 50265
|
27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7eeb4233aad5f1a1fa9853dd8052be96ee296aaab975eaf8ab53cfb58608efe8
|
3 |
-
size 997747845
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b5634cfe2312a8039ab3967c518a6f32869c348d83ffc800c525176f4c98438d
|
3 |
-
size 498863417
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0181d7e1e30a5f22b9769be65342eba1c1e28b01fe477b02a9bb3ec5d0ad3dc0
|
3 |
-
size 14575
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5709c81ed6119207bfafe582322092d4688aeb99f981a15d0a832211c0b354a5
|
3 |
-
size 627
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1,17 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": "<s>",
|
4 |
-
"cls_token": "<s>",
|
5 |
-
"eos_token": "</s>",
|
6 |
-
"errors": "replace",
|
7 |
-
"mask_token": "<mask>",
|
8 |
-
"max_len": 512,
|
9 |
-
"model_max_length": 512,
|
10 |
-
"name_or_path": "/home/pcjf/CESGA/works/lmodels/models/large",
|
11 |
-
"pad_token": "<pad>",
|
12 |
-
"sep_token": "</s>",
|
13 |
-
"special_tokens_map_file": null,
|
14 |
-
"tokenizer_class": "RobertaTokenizer",
|
15 |
-
"trim_offsets": true,
|
16 |
-
"unk_token": "<unk>"
|
17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,72 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 5.888911247253418,
|
3 |
-
"best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/large/checkpoint-6000",
|
4 |
-
"epoch": 0.86385703166126,
|
5 |
-
"global_step": 6000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.22,
|
12 |
-
"learning_rate": 7.840172786177106e-06,
|
13 |
-
"loss": 6.8838,
|
14 |
-
"step": 1500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.22,
|
18 |
-
"eval_loss": 6.199821949005127,
|
19 |
-
"eval_runtime": 80.1923,
|
20 |
-
"eval_samples_per_second": 226.281,
|
21 |
-
"eval_steps_per_second": 28.294,
|
22 |
-
"step": 1500
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"epoch": 0.43,
|
26 |
-
"learning_rate": 5.6803455723542124e-06,
|
27 |
-
"loss": 6.1582,
|
28 |
-
"step": 3000
|
29 |
-
},
|
30 |
-
{
|
31 |
-
"epoch": 0.43,
|
32 |
-
"eval_loss": 6.045103549957275,
|
33 |
-
"eval_runtime": 79.8804,
|
34 |
-
"eval_samples_per_second": 227.165,
|
35 |
-
"eval_steps_per_second": 28.405,
|
36 |
-
"step": 3000
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"epoch": 0.65,
|
40 |
-
"learning_rate": 3.520518358531318e-06,
|
41 |
-
"loss": 6.0547,
|
42 |
-
"step": 4500
|
43 |
-
},
|
44 |
-
{
|
45 |
-
"epoch": 0.65,
|
46 |
-
"eval_loss": 5.95121955871582,
|
47 |
-
"eval_runtime": 80.1607,
|
48 |
-
"eval_samples_per_second": 226.37,
|
49 |
-
"eval_steps_per_second": 28.306,
|
50 |
-
"step": 4500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.86,
|
54 |
-
"learning_rate": 1.3606911447084234e-06,
|
55 |
-
"loss": 5.9863,
|
56 |
-
"step": 6000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.86,
|
60 |
-
"eval_loss": 5.888911247253418,
|
61 |
-
"eval_runtime": 81.0425,
|
62 |
-
"eval_samples_per_second": 223.907,
|
63 |
-
"eval_steps_per_second": 27.998,
|
64 |
-
"step": 6000
|
65 |
-
}
|
66 |
-
],
|
67 |
-
"max_steps": 6945,
|
68 |
-
"num_train_epochs": 1,
|
69 |
-
"total_flos": 8.995108319836056e+16,
|
70 |
-
"trial_name": null,
|
71 |
-
"trial_params": null
|
72 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8ac315fb6f01a713c35d8bb0bc140e603ae3fc1ed639b8dd43fdc17fa5a664b6
|
3 |
-
size 3451
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
runs/Feb05_19-18-25_turing/events.out.tfevents.1675621116.turing.942264.1
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 sha256:9563588a96edafe7a32ad5535c6314e4e32abb835a745b033d3084b31f3773d8
|
3 |
+
size 5906
|