SauravMaheshkar
commited on
Commit
•
0651c83
1
Parent(s):
a0ac31e
Initial Commit
Browse files- .gitignore +2 -0
- config.json +29 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +35 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
# MacOS Stuff
|
2 |
+
**/.DS_Store
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SauravMaheshkar/xlm-roberta-base-chaii",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForQuestionAnswering"
|
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 |
+
"language": "english",
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "xlm-roberta",
|
19 |
+
"name": "XLMRoberta",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 1,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"transformers_version": "4.6.1",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250002
|
29 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f3d18795de658fe4dc1ae4644c86a110e585ca9a869cc9a10db810d2f8e02e4
|
3 |
+
size 2219761645
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88f6abc6a5e5b6f1912aaccb2bc9ac0480a2c751176fdd9ec37cb1f6f2a88b3b
|
3 |
+
size 1109908151
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03af68170e19fcf12d72bdec82d96c03f197336648b1cca79908d3bcd068e01f
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f6fe8628be0dca581f1c98aa87dab889e3aa0635bbcaf164492cd7a181fa2c7
|
3 |
+
size 623
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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": "<mask>"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null, "special_tokens_map_file": "SauravMaheshkar/xlm-roberta-base-chaii/special_tokens_map.json", "name_or_path": "SauravMaheshkar/xlm-roberta-base-chaii", "sp_model_kwargs": {}}
|
trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9994431037683311,
|
5 |
+
"global_step": 1346,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.37,
|
12 |
+
"learning_rate": 1.3971924029727499e-05,
|
13 |
+
"loss": 0.9309,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.74,
|
18 |
+
"learning_rate": 5.7142857142857145e-06,
|
19 |
+
"loss": 0.7908,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_loss": 0.9064801335334778,
|
25 |
+
"eval_runtime": 2.5516,
|
26 |
+
"eval_samples_per_second": 70.152,
|
27 |
+
"step": 1346
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"max_steps": 1346,
|
31 |
+
"num_train_epochs": 1,
|
32 |
+
"total_flos": 1.3767003962228736e+16,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": null
|
35 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54fbc8b02939a14d91737ea6c677333aa34112f3b1d9a065506cab804629a969
|
3 |
+
size 2415
|