Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- checkpoint-1200/config.json +35 -0
- checkpoint-1200/model.safetensors +3 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/sentencepiece.bpe.model +3 -0
- checkpoint-1200/special_tokens_map.json +51 -0
- checkpoint-1200/tokenizer.json +3 -0
- checkpoint-1200/tokenizer_config.json +60 -0
- checkpoint-1200/trainer_state.json +235 -0
- checkpoint-1200/training_args.bin +3 -0
- checkpoint-2000/config.json +35 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/sentencepiece.bpe.model +3 -0
- checkpoint-2000/special_tokens_map.json +51 -0
- checkpoint-2000/tokenizer.json +3 -0
- checkpoint-2000/tokenizer_config.json +60 -0
- checkpoint-2000/trainer_state.json +369 -0
- checkpoint-2000/training_args.bin +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ 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 |
+
checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1200/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT",
|
| 15 |
+
"1": "CLICKBAIT"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"CLICKBAIT": 1,
|
| 21 |
+
"NOT": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "xlm-roberta",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.57.3",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
+
}
|
checkpoint-1200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bf931ef54d0b18d461815ef2e96fdef951523851bc2b49c66c7994aadf7cfa9
|
| 3 |
+
size 2239618672
|
checkpoint-1200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a24feec8295cfece25d343ede71a9a4a926893f8b113b8c6c62061b90c47f2e
|
| 3 |
+
size 4479472785
|
checkpoint-1200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939a68f1c397249ec8d962d6c7a68f6b4fedd9115ef616df44d8cfa2ab8e4e57
|
| 3 |
+
size 14244
|
checkpoint-1200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98bc69e700d5c30663cef1077a43fc9db4c874755beafbecac040675b1a15d6d
|
| 3 |
+
size 1064
|
checkpoint-1200/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-1200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-1200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
checkpoint-1200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "<unk>"
|
| 60 |
+
}
|
checkpoint-1200/trainer_state.json
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1200,
|
| 3 |
+
"best_metric": 0.8798592637089162,
|
| 4 |
+
"best_model_checkpoint": "./clickbait_model_ua\\checkpoint-1200",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.125,
|
| 14 |
+
"grad_norm": 14.567959785461426,
|
| 15 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 16 |
+
"loss": 2.776,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.25,
|
| 21 |
+
"grad_norm": 89.11258697509766,
|
| 22 |
+
"learning_rate": 4.95e-06,
|
| 23 |
+
"loss": 1.9068,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.375,
|
| 28 |
+
"grad_norm": 29.98850440979004,
|
| 29 |
+
"learning_rate": 7.450000000000001e-06,
|
| 30 |
+
"loss": 0.645,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5,
|
| 35 |
+
"grad_norm": 0.21070414781570435,
|
| 36 |
+
"learning_rate": 9.950000000000001e-06,
|
| 37 |
+
"loss": 0.5837,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.625,
|
| 42 |
+
"grad_norm": 45.80828857421875,
|
| 43 |
+
"learning_rate": 9.727777777777777e-06,
|
| 44 |
+
"loss": 0.6524,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.75,
|
| 49 |
+
"grad_norm": 42.041900634765625,
|
| 50 |
+
"learning_rate": 9.450000000000001e-06,
|
| 51 |
+
"loss": 0.6083,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.875,
|
| 56 |
+
"grad_norm": 527.5437622070312,
|
| 57 |
+
"learning_rate": 9.172222222222223e-06,
|
| 58 |
+
"loss": 0.5635,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0,
|
| 63 |
+
"grad_norm": 0.9318615198135376,
|
| 64 |
+
"learning_rate": 8.894444444444445e-06,
|
| 65 |
+
"loss": 0.5372,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.0,
|
| 70 |
+
"eval_accuracy": 0.885,
|
| 71 |
+
"eval_f1_macro": 0.8649878195532859,
|
| 72 |
+
"eval_f1_micro": 0.885,
|
| 73 |
+
"eval_loss": 0.4778587222099304,
|
| 74 |
+
"eval_runtime": 5.7575,
|
| 75 |
+
"eval_samples_per_second": 34.737,
|
| 76 |
+
"eval_steps_per_second": 8.684,
|
| 77 |
+
"step": 400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.125,
|
| 81 |
+
"grad_norm": 0.2702992856502533,
|
| 82 |
+
"learning_rate": 8.616666666666668e-06,
|
| 83 |
+
"loss": 0.509,
|
| 84 |
+
"step": 450
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.25,
|
| 88 |
+
"grad_norm": 0.4808320999145508,
|
| 89 |
+
"learning_rate": 8.33888888888889e-06,
|
| 90 |
+
"loss": 0.4575,
|
| 91 |
+
"step": 500
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.375,
|
| 95 |
+
"grad_norm": 0.44425374269485474,
|
| 96 |
+
"learning_rate": 8.061111111111112e-06,
|
| 97 |
+
"loss": 0.4725,
|
| 98 |
+
"step": 550
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.5,
|
| 102 |
+
"grad_norm": 1.200840711593628,
|
| 103 |
+
"learning_rate": 7.783333333333334e-06,
|
| 104 |
+
"loss": 0.4814,
|
| 105 |
+
"step": 600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.625,
|
| 109 |
+
"grad_norm": 0.7429534792900085,
|
| 110 |
+
"learning_rate": 7.505555555555556e-06,
|
| 111 |
+
"loss": 0.3818,
|
| 112 |
+
"step": 650
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.75,
|
| 116 |
+
"grad_norm": 15.7191743850708,
|
| 117 |
+
"learning_rate": 7.227777777777778e-06,
|
| 118 |
+
"loss": 0.366,
|
| 119 |
+
"step": 700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.875,
|
| 123 |
+
"grad_norm": 0.05780911445617676,
|
| 124 |
+
"learning_rate": 6.95e-06,
|
| 125 |
+
"loss": 0.3609,
|
| 126 |
+
"step": 750
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.0,
|
| 130 |
+
"grad_norm": 0.12610913813114166,
|
| 131 |
+
"learning_rate": 6.672222222222223e-06,
|
| 132 |
+
"loss": 0.4139,
|
| 133 |
+
"step": 800
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.0,
|
| 137 |
+
"eval_accuracy": 0.9,
|
| 138 |
+
"eval_f1_macro": 0.877315666789351,
|
| 139 |
+
"eval_f1_micro": 0.9,
|
| 140 |
+
"eval_loss": 0.44051429629325867,
|
| 141 |
+
"eval_runtime": 6.7505,
|
| 142 |
+
"eval_samples_per_second": 29.627,
|
| 143 |
+
"eval_steps_per_second": 7.407,
|
| 144 |
+
"step": 800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.125,
|
| 148 |
+
"grad_norm": 26.771535873413086,
|
| 149 |
+
"learning_rate": 6.394444444444445e-06,
|
| 150 |
+
"loss": 0.3113,
|
| 151 |
+
"step": 850
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.25,
|
| 155 |
+
"grad_norm": 0.2790941298007965,
|
| 156 |
+
"learning_rate": 6.116666666666668e-06,
|
| 157 |
+
"loss": 0.3355,
|
| 158 |
+
"step": 900
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.375,
|
| 162 |
+
"grad_norm": 0.021798811852931976,
|
| 163 |
+
"learning_rate": 5.8388888888888895e-06,
|
| 164 |
+
"loss": 0.3901,
|
| 165 |
+
"step": 950
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.5,
|
| 169 |
+
"grad_norm": 250.39773559570312,
|
| 170 |
+
"learning_rate": 5.561111111111111e-06,
|
| 171 |
+
"loss": 0.2809,
|
| 172 |
+
"step": 1000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.625,
|
| 176 |
+
"grad_norm": 0.48538023233413696,
|
| 177 |
+
"learning_rate": 5.283333333333333e-06,
|
| 178 |
+
"loss": 0.2935,
|
| 179 |
+
"step": 1050
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.75,
|
| 183 |
+
"grad_norm": 0.16087087988853455,
|
| 184 |
+
"learning_rate": 5.005555555555556e-06,
|
| 185 |
+
"loss": 0.357,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.875,
|
| 190 |
+
"grad_norm": 0.09150100499391556,
|
| 191 |
+
"learning_rate": 4.727777777777779e-06,
|
| 192 |
+
"loss": 0.2541,
|
| 193 |
+
"step": 1150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 3.0,
|
| 197 |
+
"grad_norm": 0.12943966686725616,
|
| 198 |
+
"learning_rate": 4.450000000000001e-06,
|
| 199 |
+
"loss": 0.2905,
|
| 200 |
+
"step": 1200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0,
|
| 204 |
+
"eval_accuracy": 0.895,
|
| 205 |
+
"eval_f1_macro": 0.8798592637089162,
|
| 206 |
+
"eval_f1_micro": 0.895,
|
| 207 |
+
"eval_loss": 0.45839935541152954,
|
| 208 |
+
"eval_runtime": 8.8368,
|
| 209 |
+
"eval_samples_per_second": 22.633,
|
| 210 |
+
"eval_steps_per_second": 5.658,
|
| 211 |
+
"step": 1200
|
| 212 |
+
}
|
| 213 |
+
],
|
| 214 |
+
"logging_steps": 50,
|
| 215 |
+
"max_steps": 2000,
|
| 216 |
+
"num_input_tokens_seen": 0,
|
| 217 |
+
"num_train_epochs": 5,
|
| 218 |
+
"save_steps": 500,
|
| 219 |
+
"stateful_callbacks": {
|
| 220 |
+
"TrainerControl": {
|
| 221 |
+
"args": {
|
| 222 |
+
"should_epoch_stop": false,
|
| 223 |
+
"should_evaluate": false,
|
| 224 |
+
"should_log": false,
|
| 225 |
+
"should_save": true,
|
| 226 |
+
"should_training_stop": false
|
| 227 |
+
},
|
| 228 |
+
"attributes": {}
|
| 229 |
+
}
|
| 230 |
+
},
|
| 231 |
+
"total_flos": 2233839477897216.0,
|
| 232 |
+
"train_batch_size": 2,
|
| 233 |
+
"trial_name": null,
|
| 234 |
+
"trial_params": null
|
| 235 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ce7b1ebfee609bc511668b14f00a9900087491429dde3b8bb3f6083a129728
|
| 3 |
+
size 5432
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT",
|
| 15 |
+
"1": "CLICKBAIT"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"CLICKBAIT": 1,
|
| 21 |
+
"NOT": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "xlm-roberta",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.57.3",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3beb07a2b146245884f4d58490e7e02aaa5648955462bccccd11b13463413ac
|
| 3 |
+
size 2239618672
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fe302fe40611eb5bf5e6ecdcb76f4ddd5c4c82b3769d017935a50dbb0b70546
|
| 3 |
+
size 4479472785
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9047d0fc2b81f88a980bffd1726bd2889b9b99a462588b35d7991610cbbb44c6
|
| 3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b10f220c6245e03a350e1cc1a80f8ae24824dafeecdff977b1aa19497e2e087a
|
| 3 |
+
size 1064
|
checkpoint-2000/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "<unk>"
|
| 60 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1200,
|
| 3 |
+
"best_metric": 0.8798592637089162,
|
| 4 |
+
"best_model_checkpoint": "./clickbait_model_ua\\checkpoint-1200",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.125,
|
| 14 |
+
"grad_norm": 14.567959785461426,
|
| 15 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 16 |
+
"loss": 2.776,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.25,
|
| 21 |
+
"grad_norm": 89.11258697509766,
|
| 22 |
+
"learning_rate": 4.95e-06,
|
| 23 |
+
"loss": 1.9068,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.375,
|
| 28 |
+
"grad_norm": 29.98850440979004,
|
| 29 |
+
"learning_rate": 7.450000000000001e-06,
|
| 30 |
+
"loss": 0.645,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5,
|
| 35 |
+
"grad_norm": 0.21070414781570435,
|
| 36 |
+
"learning_rate": 9.950000000000001e-06,
|
| 37 |
+
"loss": 0.5837,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.625,
|
| 42 |
+
"grad_norm": 45.80828857421875,
|
| 43 |
+
"learning_rate": 9.727777777777777e-06,
|
| 44 |
+
"loss": 0.6524,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.75,
|
| 49 |
+
"grad_norm": 42.041900634765625,
|
| 50 |
+
"learning_rate": 9.450000000000001e-06,
|
| 51 |
+
"loss": 0.6083,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.875,
|
| 56 |
+
"grad_norm": 527.5437622070312,
|
| 57 |
+
"learning_rate": 9.172222222222223e-06,
|
| 58 |
+
"loss": 0.5635,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0,
|
| 63 |
+
"grad_norm": 0.9318615198135376,
|
| 64 |
+
"learning_rate": 8.894444444444445e-06,
|
| 65 |
+
"loss": 0.5372,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.0,
|
| 70 |
+
"eval_accuracy": 0.885,
|
| 71 |
+
"eval_f1_macro": 0.8649878195532859,
|
| 72 |
+
"eval_f1_micro": 0.885,
|
| 73 |
+
"eval_loss": 0.4778587222099304,
|
| 74 |
+
"eval_runtime": 5.7575,
|
| 75 |
+
"eval_samples_per_second": 34.737,
|
| 76 |
+
"eval_steps_per_second": 8.684,
|
| 77 |
+
"step": 400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.125,
|
| 81 |
+
"grad_norm": 0.2702992856502533,
|
| 82 |
+
"learning_rate": 8.616666666666668e-06,
|
| 83 |
+
"loss": 0.509,
|
| 84 |
+
"step": 450
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.25,
|
| 88 |
+
"grad_norm": 0.4808320999145508,
|
| 89 |
+
"learning_rate": 8.33888888888889e-06,
|
| 90 |
+
"loss": 0.4575,
|
| 91 |
+
"step": 500
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.375,
|
| 95 |
+
"grad_norm": 0.44425374269485474,
|
| 96 |
+
"learning_rate": 8.061111111111112e-06,
|
| 97 |
+
"loss": 0.4725,
|
| 98 |
+
"step": 550
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.5,
|
| 102 |
+
"grad_norm": 1.200840711593628,
|
| 103 |
+
"learning_rate": 7.783333333333334e-06,
|
| 104 |
+
"loss": 0.4814,
|
| 105 |
+
"step": 600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.625,
|
| 109 |
+
"grad_norm": 0.7429534792900085,
|
| 110 |
+
"learning_rate": 7.505555555555556e-06,
|
| 111 |
+
"loss": 0.3818,
|
| 112 |
+
"step": 650
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.75,
|
| 116 |
+
"grad_norm": 15.7191743850708,
|
| 117 |
+
"learning_rate": 7.227777777777778e-06,
|
| 118 |
+
"loss": 0.366,
|
| 119 |
+
"step": 700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.875,
|
| 123 |
+
"grad_norm": 0.05780911445617676,
|
| 124 |
+
"learning_rate": 6.95e-06,
|
| 125 |
+
"loss": 0.3609,
|
| 126 |
+
"step": 750
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.0,
|
| 130 |
+
"grad_norm": 0.12610913813114166,
|
| 131 |
+
"learning_rate": 6.672222222222223e-06,
|
| 132 |
+
"loss": 0.4139,
|
| 133 |
+
"step": 800
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.0,
|
| 137 |
+
"eval_accuracy": 0.9,
|
| 138 |
+
"eval_f1_macro": 0.877315666789351,
|
| 139 |
+
"eval_f1_micro": 0.9,
|
| 140 |
+
"eval_loss": 0.44051429629325867,
|
| 141 |
+
"eval_runtime": 6.7505,
|
| 142 |
+
"eval_samples_per_second": 29.627,
|
| 143 |
+
"eval_steps_per_second": 7.407,
|
| 144 |
+
"step": 800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.125,
|
| 148 |
+
"grad_norm": 26.771535873413086,
|
| 149 |
+
"learning_rate": 6.394444444444445e-06,
|
| 150 |
+
"loss": 0.3113,
|
| 151 |
+
"step": 850
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.25,
|
| 155 |
+
"grad_norm": 0.2790941298007965,
|
| 156 |
+
"learning_rate": 6.116666666666668e-06,
|
| 157 |
+
"loss": 0.3355,
|
| 158 |
+
"step": 900
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.375,
|
| 162 |
+
"grad_norm": 0.021798811852931976,
|
| 163 |
+
"learning_rate": 5.8388888888888895e-06,
|
| 164 |
+
"loss": 0.3901,
|
| 165 |
+
"step": 950
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.5,
|
| 169 |
+
"grad_norm": 250.39773559570312,
|
| 170 |
+
"learning_rate": 5.561111111111111e-06,
|
| 171 |
+
"loss": 0.2809,
|
| 172 |
+
"step": 1000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.625,
|
| 176 |
+
"grad_norm": 0.48538023233413696,
|
| 177 |
+
"learning_rate": 5.283333333333333e-06,
|
| 178 |
+
"loss": 0.2935,
|
| 179 |
+
"step": 1050
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.75,
|
| 183 |
+
"grad_norm": 0.16087087988853455,
|
| 184 |
+
"learning_rate": 5.005555555555556e-06,
|
| 185 |
+
"loss": 0.357,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.875,
|
| 190 |
+
"grad_norm": 0.09150100499391556,
|
| 191 |
+
"learning_rate": 4.727777777777779e-06,
|
| 192 |
+
"loss": 0.2541,
|
| 193 |
+
"step": 1150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 3.0,
|
| 197 |
+
"grad_norm": 0.12943966686725616,
|
| 198 |
+
"learning_rate": 4.450000000000001e-06,
|
| 199 |
+
"loss": 0.2905,
|
| 200 |
+
"step": 1200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0,
|
| 204 |
+
"eval_accuracy": 0.895,
|
| 205 |
+
"eval_f1_macro": 0.8798592637089162,
|
| 206 |
+
"eval_f1_micro": 0.895,
|
| 207 |
+
"eval_loss": 0.45839935541152954,
|
| 208 |
+
"eval_runtime": 8.8368,
|
| 209 |
+
"eval_samples_per_second": 22.633,
|
| 210 |
+
"eval_steps_per_second": 5.658,
|
| 211 |
+
"step": 1200
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.125,
|
| 215 |
+
"grad_norm": 0.056685227900743484,
|
| 216 |
+
"learning_rate": 4.1722222222222225e-06,
|
| 217 |
+
"loss": 0.2511,
|
| 218 |
+
"step": 1250
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.25,
|
| 222 |
+
"grad_norm": 0.32773634791374207,
|
| 223 |
+
"learning_rate": 3.894444444444444e-06,
|
| 224 |
+
"loss": 0.2644,
|
| 225 |
+
"step": 1300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.375,
|
| 229 |
+
"grad_norm": 0.7316159009933472,
|
| 230 |
+
"learning_rate": 3.616666666666667e-06,
|
| 231 |
+
"loss": 0.231,
|
| 232 |
+
"step": 1350
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.5,
|
| 236 |
+
"grad_norm": 0.22580577433109283,
|
| 237 |
+
"learning_rate": 3.3388888888888893e-06,
|
| 238 |
+
"loss": 0.2256,
|
| 239 |
+
"step": 1400
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.625,
|
| 243 |
+
"grad_norm": 0.14064151048660278,
|
| 244 |
+
"learning_rate": 3.0611111111111112e-06,
|
| 245 |
+
"loss": 0.2551,
|
| 246 |
+
"step": 1450
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.75,
|
| 250 |
+
"grad_norm": 0.2769184112548828,
|
| 251 |
+
"learning_rate": 2.7833333333333335e-06,
|
| 252 |
+
"loss": 0.2823,
|
| 253 |
+
"step": 1500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.875,
|
| 257 |
+
"grad_norm": 0.7234000563621521,
|
| 258 |
+
"learning_rate": 2.5055555555555554e-06,
|
| 259 |
+
"loss": 0.2001,
|
| 260 |
+
"step": 1550
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.0,
|
| 264 |
+
"grad_norm": 0.008039955981075764,
|
| 265 |
+
"learning_rate": 2.2277777777777777e-06,
|
| 266 |
+
"loss": 0.2275,
|
| 267 |
+
"step": 1600
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.0,
|
| 271 |
+
"eval_accuracy": 0.895,
|
| 272 |
+
"eval_f1_macro": 0.8778181818181818,
|
| 273 |
+
"eval_f1_micro": 0.895,
|
| 274 |
+
"eval_loss": 0.4554668366909027,
|
| 275 |
+
"eval_runtime": 6.561,
|
| 276 |
+
"eval_samples_per_second": 30.483,
|
| 277 |
+
"eval_steps_per_second": 7.621,
|
| 278 |
+
"step": 1600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.125,
|
| 282 |
+
"grad_norm": 0.5223516225814819,
|
| 283 |
+
"learning_rate": 1.9500000000000004e-06,
|
| 284 |
+
"loss": 0.1999,
|
| 285 |
+
"step": 1650
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.25,
|
| 289 |
+
"grad_norm": 0.7443059682846069,
|
| 290 |
+
"learning_rate": 1.6722222222222223e-06,
|
| 291 |
+
"loss": 0.2494,
|
| 292 |
+
"step": 1700
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.375,
|
| 296 |
+
"grad_norm": 0.26046261191368103,
|
| 297 |
+
"learning_rate": 1.3944444444444446e-06,
|
| 298 |
+
"loss": 0.2501,
|
| 299 |
+
"step": 1750
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.5,
|
| 303 |
+
"grad_norm": 0.09371037781238556,
|
| 304 |
+
"learning_rate": 1.1166666666666666e-06,
|
| 305 |
+
"loss": 0.2241,
|
| 306 |
+
"step": 1800
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.625,
|
| 310 |
+
"grad_norm": 0.20098061859607697,
|
| 311 |
+
"learning_rate": 8.388888888888889e-07,
|
| 312 |
+
"loss": 0.2561,
|
| 313 |
+
"step": 1850
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.75,
|
| 317 |
+
"grad_norm": 0.47540807723999023,
|
| 318 |
+
"learning_rate": 5.611111111111111e-07,
|
| 319 |
+
"loss": 0.1995,
|
| 320 |
+
"step": 1900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.875,
|
| 324 |
+
"grad_norm": 0.3193889558315277,
|
| 325 |
+
"learning_rate": 2.8333333333333336e-07,
|
| 326 |
+
"loss": 0.2103,
|
| 327 |
+
"step": 1950
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 5.0,
|
| 331 |
+
"grad_norm": 0.14755688607692719,
|
| 332 |
+
"learning_rate": 5.555555555555556e-09,
|
| 333 |
+
"loss": 0.1997,
|
| 334 |
+
"step": 2000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 5.0,
|
| 338 |
+
"eval_accuracy": 0.89,
|
| 339 |
+
"eval_f1_macro": 0.8725524272969528,
|
| 340 |
+
"eval_f1_micro": 0.89,
|
| 341 |
+
"eval_loss": 0.4618549346923828,
|
| 342 |
+
"eval_runtime": 6.5798,
|
| 343 |
+
"eval_samples_per_second": 30.396,
|
| 344 |
+
"eval_steps_per_second": 7.599,
|
| 345 |
+
"step": 2000
|
| 346 |
+
}
|
| 347 |
+
],
|
| 348 |
+
"logging_steps": 50,
|
| 349 |
+
"max_steps": 2000,
|
| 350 |
+
"num_input_tokens_seen": 0,
|
| 351 |
+
"num_train_epochs": 5,
|
| 352 |
+
"save_steps": 500,
|
| 353 |
+
"stateful_callbacks": {
|
| 354 |
+
"TrainerControl": {
|
| 355 |
+
"args": {
|
| 356 |
+
"should_epoch_stop": false,
|
| 357 |
+
"should_evaluate": false,
|
| 358 |
+
"should_log": false,
|
| 359 |
+
"should_save": true,
|
| 360 |
+
"should_training_stop": true
|
| 361 |
+
},
|
| 362 |
+
"attributes": {}
|
| 363 |
+
}
|
| 364 |
+
},
|
| 365 |
+
"total_flos": 3723065796495360.0,
|
| 366 |
+
"train_batch_size": 2,
|
| 367 |
+
"trial_name": null,
|
| 368 |
+
"trial_params": null
|
| 369 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ce7b1ebfee609bc511668b14f00a9900087491429dde3b8bb3f6083a129728
|
| 3 |
+
size 5432
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT",
|
| 15 |
+
"1": "CLICKBAIT"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"CLICKBAIT": 1,
|
| 21 |
+
"NOT": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "xlm-roberta",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.57.3",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bf931ef54d0b18d461815ef2e96fdef951523851bc2b49c66c7994aadf7cfa9
|
| 3 |
+
size 2239618672
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "<unk>"
|
| 60 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ce7b1ebfee609bc511668b14f00a9900087491429dde3b8bb3f6083a129728
|
| 3 |
+
size 5432
|