poltextlab
commited on
Commit
•
8931e4a
1
Parent(s):
fc65ab2
Upload folder using huggingface_hub
Browse files- config.json +77 -0
- pytorch_model.bin +3 -0
- tmp/checkpoint-112344/config.json +77 -0
- tmp/checkpoint-112344/optimizer.pt +3 -0
- tmp/checkpoint-112344/pytorch_model.bin +3 -0
- tmp/checkpoint-112344/rng_state.pth +3 -0
- tmp/checkpoint-112344/scheduler.pt +3 -0
- tmp/checkpoint-112344/trainer_state.json +61 -0
- tmp/checkpoint-112344/training_args.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21"
|
36 |
+
},
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": 4096,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1,
|
42 |
+
"LABEL_10": 10,
|
43 |
+
"LABEL_11": 11,
|
44 |
+
"LABEL_12": 12,
|
45 |
+
"LABEL_13": 13,
|
46 |
+
"LABEL_14": 14,
|
47 |
+
"LABEL_15": 15,
|
48 |
+
"LABEL_16": 16,
|
49 |
+
"LABEL_17": 17,
|
50 |
+
"LABEL_18": 18,
|
51 |
+
"LABEL_19": 19,
|
52 |
+
"LABEL_2": 2,
|
53 |
+
"LABEL_20": 20,
|
54 |
+
"LABEL_21": 21,
|
55 |
+
"LABEL_3": 3,
|
56 |
+
"LABEL_4": 4,
|
57 |
+
"LABEL_5": 5,
|
58 |
+
"LABEL_6": 6,
|
59 |
+
"LABEL_7": 7,
|
60 |
+
"LABEL_8": 8,
|
61 |
+
"LABEL_9": 9
|
62 |
+
},
|
63 |
+
"layer_norm_eps": 1e-05,
|
64 |
+
"max_position_embeddings": 514,
|
65 |
+
"model_type": "xlm-roberta",
|
66 |
+
"num_attention_heads": 16,
|
67 |
+
"num_hidden_layers": 24,
|
68 |
+
"output_past": true,
|
69 |
+
"pad_token_id": 1,
|
70 |
+
"position_embedding_type": "absolute",
|
71 |
+
"problem_type": "multi_label_classification",
|
72 |
+
"torch_dtype": "float32",
|
73 |
+
"transformers_version": "4.28.1",
|
74 |
+
"type_vocab_size": 1,
|
75 |
+
"use_cache": true,
|
76 |
+
"vocab_size": 250002
|
77 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562aaeb8a8026016919b06ad3e1351d5e3ed5f8263a4eb2f57f19f6a43905e3f
|
3 |
+
size 2239791925
|
tmp/checkpoint-112344/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21"
|
36 |
+
},
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": 4096,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1,
|
42 |
+
"LABEL_10": 10,
|
43 |
+
"LABEL_11": 11,
|
44 |
+
"LABEL_12": 12,
|
45 |
+
"LABEL_13": 13,
|
46 |
+
"LABEL_14": 14,
|
47 |
+
"LABEL_15": 15,
|
48 |
+
"LABEL_16": 16,
|
49 |
+
"LABEL_17": 17,
|
50 |
+
"LABEL_18": 18,
|
51 |
+
"LABEL_19": 19,
|
52 |
+
"LABEL_2": 2,
|
53 |
+
"LABEL_20": 20,
|
54 |
+
"LABEL_21": 21,
|
55 |
+
"LABEL_3": 3,
|
56 |
+
"LABEL_4": 4,
|
57 |
+
"LABEL_5": 5,
|
58 |
+
"LABEL_6": 6,
|
59 |
+
"LABEL_7": 7,
|
60 |
+
"LABEL_8": 8,
|
61 |
+
"LABEL_9": 9
|
62 |
+
},
|
63 |
+
"layer_norm_eps": 1e-05,
|
64 |
+
"max_position_embeddings": 514,
|
65 |
+
"model_type": "xlm-roberta",
|
66 |
+
"num_attention_heads": 16,
|
67 |
+
"num_hidden_layers": 24,
|
68 |
+
"output_past": true,
|
69 |
+
"pad_token_id": 1,
|
70 |
+
"position_embedding_type": "absolute",
|
71 |
+
"problem_type": "multi_label_classification",
|
72 |
+
"torch_dtype": "float32",
|
73 |
+
"transformers_version": "4.28.1",
|
74 |
+
"type_vocab_size": 1,
|
75 |
+
"use_cache": true,
|
76 |
+
"vocab_size": 250002
|
77 |
+
}
|
tmp/checkpoint-112344/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0b0ce6b4b3d5030b44854ff419cc9eeb1c6a78d5643efd4ae3506d7edb97f46
|
3 |
+
size 4479535993
|
tmp/checkpoint-112344/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562aaeb8a8026016919b06ad3e1351d5e3ed5f8263a4eb2f57f19f6a43905e3f
|
3 |
+
size 2239791925
|
tmp/checkpoint-112344/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a34756b023289bcba687335f9d6c59e6b9d08300d7677018b99e6754b45b9ce
|
3 |
+
size 14575
|
tmp/checkpoint-112344/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88eebf2ebaefc20fe5d96e7a5caa9ed1149f83080fa6740c407214a3eb160cc1
|
3 |
+
size 627
|
tmp/checkpoint-112344/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.05634467303752899,
|
3 |
+
"best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_media_5_512/tmp/checkpoint-112344",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 112344,
|
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 |
+
"learning_rate": 4.5e-06,
|
13 |
+
"loss": 0.0732,
|
14 |
+
"step": 37448
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7500934679271484,
|
19 |
+
"eval_loss": 0.05951917916536331,
|
20 |
+
"eval_runtime": 477.8656,
|
21 |
+
"eval_samples_per_second": 78.361,
|
22 |
+
"eval_steps_per_second": 9.796,
|
23 |
+
"step": 37448
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.000000000000001e-06,
|
28 |
+
"loss": 0.0547,
|
29 |
+
"step": 74896
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.7661432462746355,
|
34 |
+
"eval_loss": 0.057451553642749786,
|
35 |
+
"eval_runtime": 476.8335,
|
36 |
+
"eval_samples_per_second": 78.531,
|
37 |
+
"eval_steps_per_second": 9.817,
|
38 |
+
"step": 74896
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3.5e-06,
|
43 |
+
"loss": 0.0469,
|
44 |
+
"step": 112344
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.7781071409496342,
|
49 |
+
"eval_loss": 0.05634467303752899,
|
50 |
+
"eval_runtime": 472.9375,
|
51 |
+
"eval_samples_per_second": 79.177,
|
52 |
+
"eval_steps_per_second": 9.898,
|
53 |
+
"step": 112344
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 374480,
|
57 |
+
"num_train_epochs": 10,
|
58 |
+
"total_flos": 8.376150005616108e+17,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
tmp/checkpoint-112344/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a2cfbccc90e0714e8b654d5e5ffa9061ec5c937bb94046f1a93007aae7c7f4
|
3 |
+
size 3643
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a2cfbccc90e0714e8b654d5e5ffa9061ec5c937bb94046f1a93007aae7c7f4
|
3 |
+
size 3643
|