versae commited on
Commit
229af42
1 Parent(s): 81a2f2d

Gaussian 512 fine-tuned CoNLL 2002 es with f1/acc 0.8707/0.981

Browse files
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9810101468170739,
4
+ "eval_f1": 0.8706660583941607,
5
+ "eval_loss": 0.092462919652462,
6
+ "eval_precision": 0.8643568840579711,
7
+ "eval_recall": 0.8770680147058824,
8
+ "eval_runtime": 19.171,
9
+ "eval_samples": 1916,
10
+ "eval_samples_per_second": 99.942,
11
+ "eval_steps_per_second": 6.259,
12
+ "train_loss": 0.04096609338002562,
13
+ "train_runtime": 1383.1538,
14
+ "train_samples": 8324,
15
+ "train_samples_per_second": 30.091,
16
+ "train_steps_per_second": 1.883
17
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bertin-project/bertin-base-gaussian-exp-512seqlen",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "ner",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": 0,
16
+ "1": 1,
17
+ "2": 2,
18
+ "3": 3,
19
+ "4": 4,
20
+ "5": 5,
21
+ "6": 6,
22
+ "7": 7,
23
+ "8": 8
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "0": 0,
29
+ "1": 1,
30
+ "2": 2,
31
+ "3": 3,
32
+ "4": 4,
33
+ "5": 5,
34
+ "6": 6,
35
+ "7": 7,
36
+ "8": 8
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 514,
40
+ "model_type": "roberta",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.9.0.dev0",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9810101468170739,
4
+ "eval_f1": 0.8706660583941607,
5
+ "eval_loss": 0.092462919652462,
6
+ "eval_precision": 0.8643568840579711,
7
+ "eval_recall": 0.8770680147058824,
8
+ "eval_runtime": 19.171,
9
+ "eval_samples": 1916,
10
+ "eval_samples_per_second": 99.942,
11
+ "eval_steps_per_second": 6.259
12
+ }
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:ad8f56f5ad449dbd57ab38dae534ec652d4217cdb901ae56646a8c37352b48d5
3
+ size 496332529
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-base-gaussian-exp-512seqlen", "tokenizer_class": "RobertaTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.04096609338002562,
4
+ "train_runtime": 1383.1538,
5
+ "train_samples": 8324,
6
+ "train_samples_per_second": 30.091,
7
+ "train_steps_per_second": 1.883
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 2605,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.96,
12
+ "learning_rate": 4.040307101727447e-05,
13
+ "loss": 0.1122,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.92,
18
+ "learning_rate": 3.080614203454895e-05,
19
+ "loss": 0.0432,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.88,
24
+ "learning_rate": 2.1209213051823416e-05,
25
+ "loss": 0.0261,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.84,
30
+ "learning_rate": 1.161228406909789e-05,
31
+ "loss": 0.0177,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 4.8,
36
+ "learning_rate": 2.015355086372361e-06,
37
+ "loss": 0.0121,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 5.0,
42
+ "step": 2605,
43
+ "total_flos": 1.087585926764544e+16,
44
+ "train_loss": 0.04096609338002562,
45
+ "train_runtime": 1383.1538,
46
+ "train_samples_per_second": 30.091,
47
+ "train_steps_per_second": 1.883
48
+ }
49
+ ],
50
+ "max_steps": 2605,
51
+ "num_train_epochs": 5,
52
+ "total_flos": 1.087585926764544e+16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38809d0551f7e7d28187722f88870e0f68e199a69d8cbb477c71a26acf59dec6
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff