Spaces:
Sleeping
Sleeping
ngocminhta
commited on
Commit
·
ac85adf
1
Parent(s):
ee8f132
upload hf
Browse files
unsup-simcse-xlm-roberta-base/.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
unsup-simcse-xlm-roberta-base/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForCL"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
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": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"transformers_version": "4.2.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 250002
|
27 |
+
}
|
unsup-simcse-xlm-roberta-base/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unsup-simcse-xlm-roberta-base/trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9999040030719017,
|
5 |
+
"global_step": 1953,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.26,
|
12 |
+
"learning_rate": 7.43983614951357e-06,
|
13 |
+
"loss": 0.1187,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.51,
|
18 |
+
"learning_rate": 4.8796722990271386e-06,
|
19 |
+
"loss": 0.0011,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.77,
|
24 |
+
"learning_rate": 2.319508448540707e-06,
|
25 |
+
"loss": 0.0006,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"step": 1953,
|
31 |
+
"train_runtime": 2937.1499,
|
32 |
+
"train_samples_per_second": 0.665
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 1953,
|
36 |
+
"num_train_epochs": 1,
|
37 |
+
"total_flos": 262568325479694336,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|