Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- config.json +40 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tmp/checkpoint-2250/config.json +40 -0
- tmp/checkpoint-2250/model.safetensors +3 -0
- tmp/checkpoint-2250/optimizer.pt +3 -0
- tmp/checkpoint-2250/rng_state.pth +3 -0
- tmp/checkpoint-2250/scheduler.pt +3 -0
- tmp/checkpoint-2250/sentencepiece.bpe.model +3 -0
- tmp/checkpoint-2250/special_tokens_map.json +15 -0
- tmp/checkpoint-2250/tokenizer.json +3 -0
- tmp/checkpoint-2250/tokenizer_config.json +55 -0
- tmp/checkpoint-2250/trainer_state.json +140 -0
- tmp/checkpoint-2250/training_args.bin +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tmp/checkpoint-2250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "Destabilizing Event",
|
| 15 |
+
"1": "Precursor",
|
| 16 |
+
"2": "Resistance",
|
| 17 |
+
"3": "Symptom"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Destabilizing Event": 0,
|
| 23 |
+
"Precursor": 1,
|
| 24 |
+
"Resistance": 2,
|
| 25 |
+
"Symptom": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 514,
|
| 29 |
+
"model_type": "xlm-roberta",
|
| 30 |
+
"num_attention_heads": 16,
|
| 31 |
+
"num_hidden_layers": 24,
|
| 32 |
+
"output_past": true,
|
| 33 |
+
"pad_token_id": 1,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"transformers_version": "4.56.1",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 250002
|
| 40 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f94d097bb87b929959d40746d10e6ffff48e59a60fb1b6c5de7e4d7ab16654
|
| 3 |
+
size 2239626872
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tmp/checkpoint-2250/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "Destabilizing Event",
|
| 15 |
+
"1": "Precursor",
|
| 16 |
+
"2": "Resistance",
|
| 17 |
+
"3": "Symptom"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Destabilizing Event": 0,
|
| 23 |
+
"Precursor": 1,
|
| 24 |
+
"Resistance": 2,
|
| 25 |
+
"Symptom": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 514,
|
| 29 |
+
"model_type": "xlm-roberta",
|
| 30 |
+
"num_attention_heads": 16,
|
| 31 |
+
"num_hidden_layers": 24,
|
| 32 |
+
"output_past": true,
|
| 33 |
+
"pad_token_id": 1,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"transformers_version": "4.56.1",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 250002
|
| 40 |
+
}
|
tmp/checkpoint-2250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f94d097bb87b929959d40746d10e6ffff48e59a60fb1b6c5de7e4d7ab16654
|
| 3 |
+
size 2239626872
|
tmp/checkpoint-2250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e696f76c82ff9fba58eea445b8f4d0f86730c28670a32641b7bfc2f43b76686
|
| 3 |
+
size 4479494754
|
tmp/checkpoint-2250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12a388cb7844daa3431f45b50edcd246807d104111e46dcea512a656ba15da9d
|
| 3 |
+
size 14645
|
tmp/checkpoint-2250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4414cbd98dd6ede1678644b431edd6c52ce501218cb0897d9a14decd7e171f40
|
| 3 |
+
size 1465
|
tmp/checkpoint-2250/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
tmp/checkpoint-2250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tmp/checkpoint-2250/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
|
| 3 |
+
size 17082734
|
tmp/checkpoint-2250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
tmp/checkpoint-2250/trainer_state.json
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2250,
|
| 3 |
+
"best_metric": 0.6293792128562927,
|
| 4 |
+
"best_model_checkpoint": "model/xlm-roberta-large-deed-v01/tmp/checkpoint-2250",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.17777777777777778,
|
| 14 |
+
"grad_norm": 43.69062423706055,
|
| 15 |
+
"learning_rate": 4.911555555555556e-06,
|
| 16 |
+
"loss": 1.2401,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.35555555555555557,
|
| 21 |
+
"grad_norm": 50.24554443359375,
|
| 22 |
+
"learning_rate": 4.822666666666667e-06,
|
| 23 |
+
"loss": 0.9505,
|
| 24 |
+
"step": 400
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.5333333333333333,
|
| 28 |
+
"grad_norm": 30.88489532470703,
|
| 29 |
+
"learning_rate": 4.733777777777778e-06,
|
| 30 |
+
"loss": 0.8237,
|
| 31 |
+
"step": 600
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.7111111111111111,
|
| 35 |
+
"grad_norm": 22.756622314453125,
|
| 36 |
+
"learning_rate": 4.64488888888889e-06,
|
| 37 |
+
"loss": 0.7272,
|
| 38 |
+
"step": 800
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.8888888888888888,
|
| 42 |
+
"grad_norm": 38.99859619140625,
|
| 43 |
+
"learning_rate": 4.556e-06,
|
| 44 |
+
"loss": 0.7245,
|
| 45 |
+
"step": 1000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0,
|
| 49 |
+
"eval_accuracy": 0.7453333333333333,
|
| 50 |
+
"eval_f1": 0.6792531198405074,
|
| 51 |
+
"eval_loss": 0.6486398577690125,
|
| 52 |
+
"eval_runtime": 2.3456,
|
| 53 |
+
"eval_samples_per_second": 959.246,
|
| 54 |
+
"eval_steps_per_second": 60.113,
|
| 55 |
+
"step": 1125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.0666666666666667,
|
| 59 |
+
"grad_norm": 27.966732025146484,
|
| 60 |
+
"learning_rate": 4.467111111111111e-06,
|
| 61 |
+
"loss": 0.6686,
|
| 62 |
+
"step": 1200
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.2444444444444445,
|
| 66 |
+
"grad_norm": 19.772430419921875,
|
| 67 |
+
"learning_rate": 4.378222222222223e-06,
|
| 68 |
+
"loss": 0.6219,
|
| 69 |
+
"step": 1400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.4222222222222223,
|
| 73 |
+
"grad_norm": 39.66714096069336,
|
| 74 |
+
"learning_rate": 4.289333333333334e-06,
|
| 75 |
+
"loss": 0.6482,
|
| 76 |
+
"step": 1600
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.6,
|
| 80 |
+
"grad_norm": 44.97685623168945,
|
| 81 |
+
"learning_rate": 4.2004444444444445e-06,
|
| 82 |
+
"loss": 0.6405,
|
| 83 |
+
"step": 1800
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.7777777777777777,
|
| 87 |
+
"grad_norm": 21.78737449645996,
|
| 88 |
+
"learning_rate": 4.111555555555556e-06,
|
| 89 |
+
"loss": 0.6047,
|
| 90 |
+
"step": 2000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.9555555555555557,
|
| 94 |
+
"grad_norm": 30.245847702026367,
|
| 95 |
+
"learning_rate": 4.022666666666667e-06,
|
| 96 |
+
"loss": 0.6109,
|
| 97 |
+
"step": 2200
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.0,
|
| 101 |
+
"eval_accuracy": 0.76,
|
| 102 |
+
"eval_f1": 0.6995898342570598,
|
| 103 |
+
"eval_loss": 0.6293792128562927,
|
| 104 |
+
"eval_runtime": 2.2845,
|
| 105 |
+
"eval_samples_per_second": 984.891,
|
| 106 |
+
"eval_steps_per_second": 61.72,
|
| 107 |
+
"step": 2250
|
| 108 |
+
}
|
| 109 |
+
],
|
| 110 |
+
"logging_steps": 200,
|
| 111 |
+
"max_steps": 11250,
|
| 112 |
+
"num_input_tokens_seen": 0,
|
| 113 |
+
"num_train_epochs": 10,
|
| 114 |
+
"save_steps": 500,
|
| 115 |
+
"stateful_callbacks": {
|
| 116 |
+
"EarlyStoppingCallback": {
|
| 117 |
+
"args": {
|
| 118 |
+
"early_stopping_patience": 3,
|
| 119 |
+
"early_stopping_threshold": 0.0
|
| 120 |
+
},
|
| 121 |
+
"attributes": {
|
| 122 |
+
"early_stopping_patience_counter": 0
|
| 123 |
+
}
|
| 124 |
+
},
|
| 125 |
+
"TrainerControl": {
|
| 126 |
+
"args": {
|
| 127 |
+
"should_epoch_stop": false,
|
| 128 |
+
"should_evaluate": false,
|
| 129 |
+
"should_log": false,
|
| 130 |
+
"should_save": true,
|
| 131 |
+
"should_training_stop": false
|
| 132 |
+
},
|
| 133 |
+
"attributes": {}
|
| 134 |
+
}
|
| 135 |
+
},
|
| 136 |
+
"total_flos": 6936914382932448.0,
|
| 137 |
+
"train_batch_size": 16,
|
| 138 |
+
"trial_name": null,
|
| 139 |
+
"trial_params": null
|
| 140 |
+
}
|
tmp/checkpoint-2250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3e3b78429196a84e9c14e512dbe366621545a2c7b43e148734acdadc07836c
|
| 3 |
+
size 5777
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
|
| 3 |
+
size 17082734
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3e3b78429196a84e9c14e512dbe366621545a2c7b43e148734acdadc07836c
|
| 3 |
+
size 5777
|