Upload folder using huggingface_hub
Browse files- checkpoint-400/merges.txt +0 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +15 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer_config.json +58 -0
- checkpoint-400/trainer_state.json +423 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-400/vocab.json +0 -0
- disagreement_head.pt +3 -0
- emissions.csv +7 -0
- encoder/config.json +26 -0
- encoder/model.safetensors +3 -0
- multitask_config.json +10 -0
- target_head.pt +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +15 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +58 -0
- tokenizer/vocab.json +0 -0
checkpoint-400/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79d306454dbcdd70c3b44b639e6e2fbac508c7404f7cb2041c0026a36dcacf67
|
| 3 |
+
size 498622308
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97680250327268758ef36d8ca3c250151ce2041ff13d10893bcf51135bb99b55
|
| 3 |
+
size 113433150
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df5551a84965e2e4286feac3eb0cc9a733e6a1911fa27285c3770b04d2f8ff9a
|
| 3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5196e8b6283bd73106905dbe14b86ceb960ef41a766cd494be7b8cb7159902e
|
| 3 |
+
size 1064
|
checkpoint-400/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 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 400,
|
| 3 |
+
"best_metric": 1.027809500694275,
|
| 4 |
+
"best_model_checkpoint": "./multitask_model2/checkpoint-400",
|
| 5 |
+
"epoch": 20.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 2.2844085693359375,
|
| 15 |
+
"learning_rate": 1.9050000000000002e-05,
|
| 16 |
+
"loss": 1.1853,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_disagreement_accuracy": 0.6258992805755396,
|
| 22 |
+
"eval_disagreement_f1": 0.7699115044247787,
|
| 23 |
+
"eval_loss": 1.112855315208435,
|
| 24 |
+
"eval_runtime": 1.0766,
|
| 25 |
+
"eval_samples_per_second": 129.108,
|
| 26 |
+
"eval_steps_per_second": 4.644,
|
| 27 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 28 |
+
"eval_target_f1": 0.14175257731958762,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 1.3726364374160767,
|
| 34 |
+
"learning_rate": 1.805e-05,
|
| 35 |
+
"loss": 1.1313,
|
| 36 |
+
"step": 40
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_disagreement_accuracy": 0.6258992805755396,
|
| 41 |
+
"eval_disagreement_f1": 0.7699115044247787,
|
| 42 |
+
"eval_loss": 1.1013033390045166,
|
| 43 |
+
"eval_runtime": 1.0723,
|
| 44 |
+
"eval_samples_per_second": 129.63,
|
| 45 |
+
"eval_steps_per_second": 4.663,
|
| 46 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 47 |
+
"eval_target_f1": 0.14175257731958762,
|
| 48 |
+
"step": 40
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"grad_norm": 1.70554780960083,
|
| 53 |
+
"learning_rate": 1.705e-05,
|
| 54 |
+
"loss": 1.143,
|
| 55 |
+
"step": 60
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.0,
|
| 59 |
+
"eval_disagreement_accuracy": 0.6258992805755396,
|
| 60 |
+
"eval_disagreement_f1": 0.7699115044247787,
|
| 61 |
+
"eval_loss": 1.1059356927871704,
|
| 62 |
+
"eval_runtime": 1.076,
|
| 63 |
+
"eval_samples_per_second": 129.179,
|
| 64 |
+
"eval_steps_per_second": 4.647,
|
| 65 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 66 |
+
"eval_target_f1": 0.14175257731958762,
|
| 67 |
+
"step": 60
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 4.0,
|
| 71 |
+
"grad_norm": 1.1046576499938965,
|
| 72 |
+
"learning_rate": 1.605e-05,
|
| 73 |
+
"loss": 1.1277,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"eval_disagreement_accuracy": 0.49640287769784175,
|
| 79 |
+
"eval_disagreement_f1": 0.573170731707317,
|
| 80 |
+
"eval_loss": 1.1105602979660034,
|
| 81 |
+
"eval_runtime": 1.042,
|
| 82 |
+
"eval_samples_per_second": 133.398,
|
| 83 |
+
"eval_steps_per_second": 4.798,
|
| 84 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 85 |
+
"eval_target_f1": 0.14175257731958762,
|
| 86 |
+
"step": 80
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.0,
|
| 90 |
+
"grad_norm": 1.312771201133728,
|
| 91 |
+
"learning_rate": 1.505e-05,
|
| 92 |
+
"loss": 1.1332,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 5.0,
|
| 97 |
+
"eval_disagreement_accuracy": 0.37410071942446044,
|
| 98 |
+
"eval_disagreement_f1": 0.02247191011235955,
|
| 99 |
+
"eval_loss": 1.1022462844848633,
|
| 100 |
+
"eval_runtime": 1.0546,
|
| 101 |
+
"eval_samples_per_second": 131.802,
|
| 102 |
+
"eval_steps_per_second": 4.741,
|
| 103 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 104 |
+
"eval_target_f1": 0.14175257731958762,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.0,
|
| 109 |
+
"grad_norm": 2.6298487186431885,
|
| 110 |
+
"learning_rate": 1.4050000000000001e-05,
|
| 111 |
+
"loss": 1.134,
|
| 112 |
+
"step": 120
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.0,
|
| 116 |
+
"eval_disagreement_accuracy": 0.4316546762589928,
|
| 117 |
+
"eval_disagreement_f1": 0.368,
|
| 118 |
+
"eval_loss": 1.1018866300582886,
|
| 119 |
+
"eval_runtime": 1.0637,
|
| 120 |
+
"eval_samples_per_second": 130.671,
|
| 121 |
+
"eval_steps_per_second": 4.7,
|
| 122 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 123 |
+
"eval_target_f1": 0.14175257731958762,
|
| 124 |
+
"step": 120
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 7.0,
|
| 128 |
+
"grad_norm": 2.4779446125030518,
|
| 129 |
+
"learning_rate": 1.305e-05,
|
| 130 |
+
"loss": 1.1311,
|
| 131 |
+
"step": 140
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 7.0,
|
| 135 |
+
"eval_disagreement_accuracy": 0.48201438848920863,
|
| 136 |
+
"eval_disagreement_f1": 0.52,
|
| 137 |
+
"eval_loss": 1.0945336818695068,
|
| 138 |
+
"eval_runtime": 1.0649,
|
| 139 |
+
"eval_samples_per_second": 130.524,
|
| 140 |
+
"eval_steps_per_second": 4.695,
|
| 141 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 142 |
+
"eval_target_f1": 0.14175257731958762,
|
| 143 |
+
"step": 140
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 8.0,
|
| 147 |
+
"grad_norm": 2.918020009994507,
|
| 148 |
+
"learning_rate": 1.2050000000000002e-05,
|
| 149 |
+
"loss": 1.1108,
|
| 150 |
+
"step": 160
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_disagreement_accuracy": 0.4460431654676259,
|
| 155 |
+
"eval_disagreement_f1": 0.37398373983739835,
|
| 156 |
+
"eval_loss": 1.091244101524353,
|
| 157 |
+
"eval_runtime": 1.078,
|
| 158 |
+
"eval_samples_per_second": 128.947,
|
| 159 |
+
"eval_steps_per_second": 4.638,
|
| 160 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 161 |
+
"eval_target_f1": 0.14175257731958762,
|
| 162 |
+
"step": 160
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.0,
|
| 166 |
+
"grad_norm": 2.117605447769165,
|
| 167 |
+
"learning_rate": 1.1050000000000001e-05,
|
| 168 |
+
"loss": 1.1137,
|
| 169 |
+
"step": 180
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"eval_disagreement_accuracy": 0.39568345323741005,
|
| 174 |
+
"eval_disagreement_f1": 0.20754716981132076,
|
| 175 |
+
"eval_loss": 1.084085464477539,
|
| 176 |
+
"eval_runtime": 1.074,
|
| 177 |
+
"eval_samples_per_second": 129.426,
|
| 178 |
+
"eval_steps_per_second": 4.656,
|
| 179 |
+
"eval_target_accuracy": 0.39568345323741005,
|
| 180 |
+
"eval_target_f1": 0.14175257731958762,
|
| 181 |
+
"step": 180
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 10.0,
|
| 185 |
+
"grad_norm": 3.1829466819763184,
|
| 186 |
+
"learning_rate": 1.005e-05,
|
| 187 |
+
"loss": 1.0945,
|
| 188 |
+
"step": 200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.0,
|
| 192 |
+
"eval_disagreement_accuracy": 0.49640287769784175,
|
| 193 |
+
"eval_disagreement_f1": 0.5679012345679012,
|
| 194 |
+
"eval_loss": 1.0726532936096191,
|
| 195 |
+
"eval_runtime": 1.0747,
|
| 196 |
+
"eval_samples_per_second": 129.339,
|
| 197 |
+
"eval_steps_per_second": 4.652,
|
| 198 |
+
"eval_target_accuracy": 0.4028776978417266,
|
| 199 |
+
"eval_target_f1": 0.16100556515064288,
|
| 200 |
+
"step": 200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 11.0,
|
| 204 |
+
"grad_norm": 4.089995384216309,
|
| 205 |
+
"learning_rate": 9.050000000000001e-06,
|
| 206 |
+
"loss": 1.0823,
|
| 207 |
+
"step": 220
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 11.0,
|
| 211 |
+
"eval_disagreement_accuracy": 0.5683453237410072,
|
| 212 |
+
"eval_disagreement_f1": 0.6938775510204082,
|
| 213 |
+
"eval_loss": 1.0664323568344116,
|
| 214 |
+
"eval_runtime": 1.0642,
|
| 215 |
+
"eval_samples_per_second": 130.611,
|
| 216 |
+
"eval_steps_per_second": 4.698,
|
| 217 |
+
"eval_target_accuracy": 0.4676258992805755,
|
| 218 |
+
"eval_target_f1": 0.3595999843743896,
|
| 219 |
+
"step": 220
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.0,
|
| 223 |
+
"grad_norm": 6.042879581451416,
|
| 224 |
+
"learning_rate": 8.050000000000001e-06,
|
| 225 |
+
"loss": 1.0485,
|
| 226 |
+
"step": 240
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 12.0,
|
| 230 |
+
"eval_disagreement_accuracy": 0.6115107913669064,
|
| 231 |
+
"eval_disagreement_f1": 0.7428571428571429,
|
| 232 |
+
"eval_loss": 1.0571434497833252,
|
| 233 |
+
"eval_runtime": 1.0743,
|
| 234 |
+
"eval_samples_per_second": 129.385,
|
| 235 |
+
"eval_steps_per_second": 4.654,
|
| 236 |
+
"eval_target_accuracy": 0.4460431654676259,
|
| 237 |
+
"eval_target_f1": 0.4093454949547387,
|
| 238 |
+
"step": 240
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.0,
|
| 242 |
+
"grad_norm": 8.205199241638184,
|
| 243 |
+
"learning_rate": 7.05e-06,
|
| 244 |
+
"loss": 1.037,
|
| 245 |
+
"step": 260
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.0,
|
| 249 |
+
"eval_disagreement_accuracy": 0.5683453237410072,
|
| 250 |
+
"eval_disagreement_f1": 0.6907216494845361,
|
| 251 |
+
"eval_loss": 1.0401602983474731,
|
| 252 |
+
"eval_runtime": 1.071,
|
| 253 |
+
"eval_samples_per_second": 129.791,
|
| 254 |
+
"eval_steps_per_second": 4.669,
|
| 255 |
+
"eval_target_accuracy": 0.4460431654676259,
|
| 256 |
+
"eval_target_f1": 0.4108350863328026,
|
| 257 |
+
"step": 260
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 14.0,
|
| 261 |
+
"grad_norm": 5.9651198387146,
|
| 262 |
+
"learning_rate": 6.0500000000000005e-06,
|
| 263 |
+
"loss": 0.9871,
|
| 264 |
+
"step": 280
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 14.0,
|
| 268 |
+
"eval_disagreement_accuracy": 0.5611510791366906,
|
| 269 |
+
"eval_disagreement_f1": 0.6737967914438503,
|
| 270 |
+
"eval_loss": 1.044658899307251,
|
| 271 |
+
"eval_runtime": 1.0738,
|
| 272 |
+
"eval_samples_per_second": 129.45,
|
| 273 |
+
"eval_steps_per_second": 4.656,
|
| 274 |
+
"eval_target_accuracy": 0.4244604316546763,
|
| 275 |
+
"eval_target_f1": 0.4027126310560305,
|
| 276 |
+
"step": 280
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 15.0,
|
| 280 |
+
"grad_norm": 7.971250057220459,
|
| 281 |
+
"learning_rate": 5.050000000000001e-06,
|
| 282 |
+
"loss": 0.9755,
|
| 283 |
+
"step": 300
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 15.0,
|
| 287 |
+
"eval_disagreement_accuracy": 0.5251798561151079,
|
| 288 |
+
"eval_disagreement_f1": 0.625,
|
| 289 |
+
"eval_loss": 1.031907558441162,
|
| 290 |
+
"eval_runtime": 1.0497,
|
| 291 |
+
"eval_samples_per_second": 132.417,
|
| 292 |
+
"eval_steps_per_second": 4.763,
|
| 293 |
+
"eval_target_accuracy": 0.4316546762589928,
|
| 294 |
+
"eval_target_f1": 0.3930631467390657,
|
| 295 |
+
"step": 300
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 16.0,
|
| 299 |
+
"grad_norm": 7.735967636108398,
|
| 300 |
+
"learning_rate": 4.05e-06,
|
| 301 |
+
"loss": 0.9793,
|
| 302 |
+
"step": 320
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 16.0,
|
| 306 |
+
"eval_disagreement_accuracy": 0.539568345323741,
|
| 307 |
+
"eval_disagreement_f1": 0.6404494382022472,
|
| 308 |
+
"eval_loss": 1.028196930885315,
|
| 309 |
+
"eval_runtime": 1.0874,
|
| 310 |
+
"eval_samples_per_second": 127.832,
|
| 311 |
+
"eval_steps_per_second": 4.598,
|
| 312 |
+
"eval_target_accuracy": 0.4460431654676259,
|
| 313 |
+
"eval_target_f1": 0.4001030960796005,
|
| 314 |
+
"step": 320
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 17.0,
|
| 318 |
+
"grad_norm": 10.927641868591309,
|
| 319 |
+
"learning_rate": 3.05e-06,
|
| 320 |
+
"loss": 0.9547,
|
| 321 |
+
"step": 340
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 17.0,
|
| 325 |
+
"eval_disagreement_accuracy": 0.5107913669064749,
|
| 326 |
+
"eval_disagreement_f1": 0.5952380952380952,
|
| 327 |
+
"eval_loss": 1.0321024656295776,
|
| 328 |
+
"eval_runtime": 1.0659,
|
| 329 |
+
"eval_samples_per_second": 130.402,
|
| 330 |
+
"eval_steps_per_second": 4.691,
|
| 331 |
+
"eval_target_accuracy": 0.43884892086330934,
|
| 332 |
+
"eval_target_f1": 0.41229973730588904,
|
| 333 |
+
"step": 340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 18.0,
|
| 337 |
+
"grad_norm": 8.823258399963379,
|
| 338 |
+
"learning_rate": 2.05e-06,
|
| 339 |
+
"loss": 0.9564,
|
| 340 |
+
"step": 360
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 18.0,
|
| 344 |
+
"eval_disagreement_accuracy": 0.5035971223021583,
|
| 345 |
+
"eval_disagreement_f1": 0.5714285714285714,
|
| 346 |
+
"eval_loss": 1.0311119556427002,
|
| 347 |
+
"eval_runtime": 1.0907,
|
| 348 |
+
"eval_samples_per_second": 127.442,
|
| 349 |
+
"eval_steps_per_second": 4.584,
|
| 350 |
+
"eval_target_accuracy": 0.43884892086330934,
|
| 351 |
+
"eval_target_f1": 0.4117807336094353,
|
| 352 |
+
"step": 360
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 19.0,
|
| 356 |
+
"grad_norm": 7.3762898445129395,
|
| 357 |
+
"learning_rate": 1.0500000000000001e-06,
|
| 358 |
+
"loss": 0.9542,
|
| 359 |
+
"step": 380
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 19.0,
|
| 363 |
+
"eval_disagreement_accuracy": 0.4460431654676259,
|
| 364 |
+
"eval_disagreement_f1": 0.48322147651006714,
|
| 365 |
+
"eval_loss": 1.0291540622711182,
|
| 366 |
+
"eval_runtime": 1.0597,
|
| 367 |
+
"eval_samples_per_second": 131.163,
|
| 368 |
+
"eval_steps_per_second": 4.718,
|
| 369 |
+
"eval_target_accuracy": 0.43884892086330934,
|
| 370 |
+
"eval_target_f1": 0.40460400616332826,
|
| 371 |
+
"step": 380
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 20.0,
|
| 375 |
+
"grad_norm": 12.848645210266113,
|
| 376 |
+
"learning_rate": 5.0000000000000004e-08,
|
| 377 |
+
"loss": 0.9522,
|
| 378 |
+
"step": 400
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 20.0,
|
| 382 |
+
"eval_disagreement_accuracy": 0.4748201438848921,
|
| 383 |
+
"eval_disagreement_f1": 0.5290322580645161,
|
| 384 |
+
"eval_loss": 1.027809500694275,
|
| 385 |
+
"eval_runtime": 1.074,
|
| 386 |
+
"eval_samples_per_second": 129.427,
|
| 387 |
+
"eval_steps_per_second": 4.656,
|
| 388 |
+
"eval_target_accuracy": 0.4244604316546763,
|
| 389 |
+
"eval_target_f1": 0.39001237557169766,
|
| 390 |
+
"step": 400
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"logging_steps": 500,
|
| 394 |
+
"max_steps": 400,
|
| 395 |
+
"num_input_tokens_seen": 0,
|
| 396 |
+
"num_train_epochs": 20,
|
| 397 |
+
"save_steps": 500,
|
| 398 |
+
"stateful_callbacks": {
|
| 399 |
+
"EarlyStoppingCallback": {
|
| 400 |
+
"args": {
|
| 401 |
+
"early_stopping_patience": 5,
|
| 402 |
+
"early_stopping_threshold": 0.0
|
| 403 |
+
},
|
| 404 |
+
"attributes": {
|
| 405 |
+
"early_stopping_patience_counter": 0
|
| 406 |
+
}
|
| 407 |
+
},
|
| 408 |
+
"TrainerControl": {
|
| 409 |
+
"args": {
|
| 410 |
+
"should_epoch_stop": false,
|
| 411 |
+
"should_evaluate": false,
|
| 412 |
+
"should_log": false,
|
| 413 |
+
"should_save": true,
|
| 414 |
+
"should_training_stop": true
|
| 415 |
+
},
|
| 416 |
+
"attributes": {}
|
| 417 |
+
}
|
| 418 |
+
},
|
| 419 |
+
"total_flos": 0.0,
|
| 420 |
+
"train_batch_size": 32,
|
| 421 |
+
"trial_name": null,
|
| 422 |
+
"trial_params": null
|
| 423 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f32b0cf3c27c444da01e7312faa99aadf87ec2a1877a2c08fc94b51f49f45092
|
| 3 |
+
size 5368
|
checkpoint-400/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
disagreement_head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ff36804293ed04ae495f01581cc3bb6e9f59226ded0e9fd800c562f69ebae0f
|
| 3 |
+
size 4756
|
emissions.csv
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,water_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue,wue
|
| 2 |
+
2025-12-27T09:22:48,codecarbon,8dd21937-b8e5-4f79-8ad0-f57154e101df,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,169.4342174604535,0.0092895587518505,5.482693455363415e-05,46.006017593500005,376.08024016363873,70.0,0.0021651028122146,0.0227533029248547,0.0031706573071268,0.0280890630441962,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
| 3 |
+
2025-12-27T09:28:50,codecarbon,18b34d90-a229-4fe6-89ec-3a5110deffd1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,172.1621928922832,0.0091464098204684,5.312670376004736e-05,46.004093632000014,435.9794106020623,70.0,0.0021229984786781,0.0223037733985478,0.0032294482875925,0.0276562201648185,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
| 4 |
+
2025-12-27T09:33:47,codecarbon,b7827b45-10fb-409c-bb38-2fc36f5b9ef1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,170.79744918830693,0.0087805626784695,5.140921436589374e-05,46.005528211000005,419.5694036221124,70.0,0.0021053042642194,0.0212416214377384,0.003203073628195,0.0265499993301529,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
| 5 |
+
2025-12-27T09:40:13,codecarbon,6af5ad3b-722e-48c2-bb5e-6f1258123a4a,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,173.3182188104838,0.0094243748730559,5.437613505225987e-05,46.00488524600001,441.7163012983281,70.0,0.0021377607276174,0.0231071451523661,0.0032518039243088,0.0284967098042924,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
| 6 |
+
2025-12-27T09:46:45,codecarbon,f89fc66d-4969-489a-a610-9f83bb4df606,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,171.55705239251256,0.0087719280544175,5.113125885578832e-05,46.00544065,426.0873453904788,70.0,0.002115152569705,0.0211908063970582,0.0032179316422074,0.0265238906089707,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
| 7 |
+
2025-12-27T09:52:10,codecarbon,d9ada08f-102d-4554-acd5-8fa07cebe582,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,170.87246932834387,0.008755401116170982,5.123939011700499e-05,46.004816476,403.25555317378127,70.0,0.0021062079524079343,0.021163356652891707,0.003204353101541185,0.026473917706840818,0.0,Italy,ITA,tuscany,,,Linux-5.4.0-216-generic-x86_64-with-glibc2.31,3.10.18,3.0.8,96,Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz,2,2 x NVIDIA RTX A6000,10.4326,43.7667,1007.494571685791,machine,N,1.0,0.0
|
encoder/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaModel"
|
| 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": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"transformers_version": "4.57.1",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50265
|
| 26 |
+
}
|
encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6ca91ad07bec0979dec93278b5f172823d1959d49baa39ceae7a5180916ab90
|
| 3 |
+
size 498604904
|
multitask_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "multitask_roberta",
|
| 3 |
+
"base_model": "FacebookAI/roberta-base",
|
| 4 |
+
"task_labels_map": {
|
| 5 |
+
"disagreement": 1,
|
| 6 |
+
"target": 1
|
| 7 |
+
},
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"dropout_prob": 0.4
|
| 10 |
+
}
|
target_head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1efcb099973cf7f89a78cbca675882a375767a3096331f193bfcb7aaf1079b1f
|
| 3 |
+
size 13872
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/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 |
+
}
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|