poltextlab
commited on
Commit
•
a6253c8
1
Parent(s):
8f0c042
Upload folder using huggingface_hub
Browse files- config.json +77 -0
- pytorch_model.bin +3 -0
- tmp/checkpoint-6840/config.json +77 -0
- tmp/checkpoint-6840/optimizer.pt +3 -0
- tmp/checkpoint-6840/pytorch_model.bin +3 -0
- tmp/checkpoint-6840/rng_state.pth +3 -0
- tmp/checkpoint-6840/scheduler.pt +3 -0
- tmp/checkpoint-6840/trainer_state.json +61 -0
- tmp/checkpoint-6840/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:aa3b77289a1d33746b16f6168b9c6d721ce0237dc3189700528ae6242ded2f5a
|
3 |
+
size 2239791925
|
tmp/checkpoint-6840/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-6840/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49262b642e91ceb52734f7ddcc999772d1e123c48764f2487fd91651c245ae0
|
3 |
+
size 4479535225
|
tmp/checkpoint-6840/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa3b77289a1d33746b16f6168b9c6d721ce0237dc3189700528ae6242ded2f5a
|
3 |
+
size 2239791925
|
tmp/checkpoint-6840/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7ef08157d1e5aaebf2ee922edd00a99d212fa06e507394fbb6795f38c059b19
|
3 |
+
size 14575
|
tmp/checkpoint-6840/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61652a58d5e3286f8cf21c91b659bd7a8c2e30f48c46646954b2466da9443aaa
|
3 |
+
size 627
|
tmp/checkpoint-6840/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.07112815976142883,
|
3 |
+
"best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_french_5_512/tmp/checkpoint-6840",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 6840,
|
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": 0.1391,
|
14 |
+
"step": 2280
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7017543859649122,
|
19 |
+
"eval_loss": 0.08547523617744446,
|
20 |
+
"eval_runtime": 56.0096,
|
21 |
+
"eval_samples_per_second": 40.707,
|
22 |
+
"eval_steps_per_second": 5.088,
|
23 |
+
"step": 2280
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.000000000000001e-06,
|
28 |
+
"loss": 0.0803,
|
29 |
+
"step": 4560
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.7263157894736842,
|
34 |
+
"eval_loss": 0.07496826350688934,
|
35 |
+
"eval_runtime": 55.7373,
|
36 |
+
"eval_samples_per_second": 40.906,
|
37 |
+
"eval_steps_per_second": 5.113,
|
38 |
+
"step": 4560
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3.5e-06,
|
43 |
+
"loss": 0.0654,
|
44 |
+
"step": 6840
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.7328947368421053,
|
49 |
+
"eval_loss": 0.07112815976142883,
|
50 |
+
"eval_runtime": 56.0517,
|
51 |
+
"eval_samples_per_second": 40.677,
|
52 |
+
"eval_steps_per_second": 5.085,
|
53 |
+
"step": 6840
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 22800,
|
57 |
+
"num_train_epochs": 10,
|
58 |
+
"total_flos": 5.098754631595622e+16,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
tmp/checkpoint-6840/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df183d999f759d489f34e2beec093fc26b02ede4e6e5f225ac8e979fcdbbd6d4
|
3 |
+
size 3643
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df183d999f759d489f34e2beec093fc26b02ede4e6e5f225ac8e979fcdbbd6d4
|
3 |
+
size 3643
|