Upload folder using huggingface_hub
Browse files- checkpoint-9213/config.json +69 -0
- checkpoint-9213/generation_config.json +7 -0
- checkpoint-9213/model.safetensors +3 -0
- checkpoint-9213/optimizer.pt +3 -0
- checkpoint-9213/rng_state.pth +3 -0
- checkpoint-9213/scaler.pt +3 -0
- checkpoint-9213/scheduler.pt +3 -0
- checkpoint-9213/tokenizer.json +0 -0
- checkpoint-9213/tokenizer_config.json +719 -0
- checkpoint-9213/trainer_state.json +1361 -0
- checkpoint-9213/training_args.bin +3 -0
- config.json +4 -3
- generation_config.json +1 -1
- model.safetensors +1 -1
- tokenizer.json +16 -954
- tokenizer_config.json +204 -445
checkpoint-9213/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"dtype": "float32",
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"feed_forward_proj": "relu",
|
| 16 |
+
"gradient_checkpointing": false,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "LABEL_0"
|
| 19 |
+
},
|
| 20 |
+
"initializer_factor": 1.0,
|
| 21 |
+
"is_encoder_decoder": true,
|
| 22 |
+
"is_gated_act": false,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_epsilon": 1e-06,
|
| 27 |
+
"model_type": "t5",
|
| 28 |
+
"n_positions": 512,
|
| 29 |
+
"num_decoder_layers": 12,
|
| 30 |
+
"num_heads": 12,
|
| 31 |
+
"num_layers": 12,
|
| 32 |
+
"output_past": true,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"relative_attention_max_distance": 128,
|
| 35 |
+
"relative_attention_num_buckets": 32,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"summarization": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"length_penalty": 2.0,
|
| 40 |
+
"max_length": 200,
|
| 41 |
+
"min_length": 30,
|
| 42 |
+
"no_repeat_ngram_size": 3,
|
| 43 |
+
"num_beams": 4,
|
| 44 |
+
"prefix": "summarize: "
|
| 45 |
+
},
|
| 46 |
+
"translation_en_to_de": {
|
| 47 |
+
"early_stopping": true,
|
| 48 |
+
"max_length": 300,
|
| 49 |
+
"num_beams": 4,
|
| 50 |
+
"prefix": "translate English to German: "
|
| 51 |
+
},
|
| 52 |
+
"translation_en_to_fr": {
|
| 53 |
+
"early_stopping": true,
|
| 54 |
+
"max_length": 300,
|
| 55 |
+
"num_beams": 4,
|
| 56 |
+
"prefix": "translate English to French: "
|
| 57 |
+
},
|
| 58 |
+
"translation_en_to_ro": {
|
| 59 |
+
"early_stopping": true,
|
| 60 |
+
"max_length": 300,
|
| 61 |
+
"num_beams": 4,
|
| 62 |
+
"prefix": "translate English to Romanian: "
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
"tie_encoder_decoder": true,
|
| 66 |
+
"transformers_version": "5.0.0rc0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 32100
|
| 69 |
+
}
|
checkpoint-9213/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.0.0rc0"
|
| 7 |
+
}
|
checkpoint-9213/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:414c84be0b79007c8b483dfa0edc614683a246cb00481cf2e7649a09ab4718e6
|
| 3 |
+
size 891558696
|
checkpoint-9213/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571fb027670013787f20d47f26a00ef17b3bcf57c205a5f326b725eb8494fd4e
|
| 3 |
+
size 1783272762
|
checkpoint-9213/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26dabb5cba7d4a2b48b61ec07b4c6c2cfdfdeb8ed15dbdd4779dfdca45607b72
|
| 3 |
+
size 14244
|
checkpoint-9213/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e68867f3698ac8ea7797dc967883d9031fa55d0abf3ced96a441297292d5b8e
|
| 3 |
+
size 988
|
checkpoint-9213/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34c32812a45193caeaa27777aed850d8d384d32b9ae4402199dcc3cb9225ad44
|
| 3 |
+
size 1064
|
checkpoint-9213/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-9213/tokenizer_config.json
ADDED
|
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"additional_special_tokens": [
|
| 4 |
+
{
|
| 5 |
+
"content": "<extra_id_99>",
|
| 6 |
+
"lstrip": true,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"content": "<extra_id_98>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"content": "<extra_id_97>",
|
| 20 |
+
"lstrip": true,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"content": "<extra_id_96>",
|
| 27 |
+
"lstrip": true,
|
| 28 |
+
"normalized": true,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"content": "<extra_id_95>",
|
| 34 |
+
"lstrip": true,
|
| 35 |
+
"normalized": true,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"content": "<extra_id_94>",
|
| 41 |
+
"lstrip": true,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"content": "<extra_id_93>",
|
| 48 |
+
"lstrip": true,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"content": "<extra_id_92>",
|
| 55 |
+
"lstrip": true,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"content": "<extra_id_91>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"content": "<extra_id_90>",
|
| 69 |
+
"lstrip": true,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"content": "<extra_id_89>",
|
| 76 |
+
"lstrip": true,
|
| 77 |
+
"normalized": true,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"single_word": false
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"content": "<extra_id_88>",
|
| 83 |
+
"lstrip": true,
|
| 84 |
+
"normalized": true,
|
| 85 |
+
"rstrip": false,
|
| 86 |
+
"single_word": false
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"content": "<extra_id_87>",
|
| 90 |
+
"lstrip": true,
|
| 91 |
+
"normalized": true,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"single_word": false
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"content": "<extra_id_86>",
|
| 97 |
+
"lstrip": true,
|
| 98 |
+
"normalized": true,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"single_word": false
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"content": "<extra_id_85>",
|
| 104 |
+
"lstrip": true,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"content": "<extra_id_84>",
|
| 111 |
+
"lstrip": true,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"content": "<extra_id_83>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"content": "<extra_id_82>",
|
| 125 |
+
"lstrip": true,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"content": "<extra_id_81>",
|
| 132 |
+
"lstrip": true,
|
| 133 |
+
"normalized": true,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"single_word": false
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"content": "<extra_id_80>",
|
| 139 |
+
"lstrip": true,
|
| 140 |
+
"normalized": true,
|
| 141 |
+
"rstrip": false,
|
| 142 |
+
"single_word": false
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"content": "<extra_id_79>",
|
| 146 |
+
"lstrip": true,
|
| 147 |
+
"normalized": true,
|
| 148 |
+
"rstrip": false,
|
| 149 |
+
"single_word": false
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"content": "<extra_id_78>",
|
| 153 |
+
"lstrip": true,
|
| 154 |
+
"normalized": true,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"single_word": false
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"content": "<extra_id_77>",
|
| 160 |
+
"lstrip": true,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"content": "<extra_id_76>",
|
| 167 |
+
"lstrip": true,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"content": "<extra_id_75>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"content": "<extra_id_74>",
|
| 181 |
+
"lstrip": true,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"content": "<extra_id_73>",
|
| 188 |
+
"lstrip": true,
|
| 189 |
+
"normalized": true,
|
| 190 |
+
"rstrip": false,
|
| 191 |
+
"single_word": false
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"content": "<extra_id_72>",
|
| 195 |
+
"lstrip": true,
|
| 196 |
+
"normalized": true,
|
| 197 |
+
"rstrip": false,
|
| 198 |
+
"single_word": false
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"content": "<extra_id_71>",
|
| 202 |
+
"lstrip": true,
|
| 203 |
+
"normalized": true,
|
| 204 |
+
"rstrip": false,
|
| 205 |
+
"single_word": false
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"content": "<extra_id_70>",
|
| 209 |
+
"lstrip": true,
|
| 210 |
+
"normalized": true,
|
| 211 |
+
"rstrip": false,
|
| 212 |
+
"single_word": false
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"content": "<extra_id_69>",
|
| 216 |
+
"lstrip": true,
|
| 217 |
+
"normalized": true,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"content": "<extra_id_68>",
|
| 223 |
+
"lstrip": true,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"content": "<extra_id_67>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"content": "<extra_id_66>",
|
| 237 |
+
"lstrip": true,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"content": "<extra_id_65>",
|
| 244 |
+
"lstrip": true,
|
| 245 |
+
"normalized": true,
|
| 246 |
+
"rstrip": false,
|
| 247 |
+
"single_word": false
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"content": "<extra_id_64>",
|
| 251 |
+
"lstrip": true,
|
| 252 |
+
"normalized": true,
|
| 253 |
+
"rstrip": false,
|
| 254 |
+
"single_word": false
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"content": "<extra_id_63>",
|
| 258 |
+
"lstrip": true,
|
| 259 |
+
"normalized": true,
|
| 260 |
+
"rstrip": false,
|
| 261 |
+
"single_word": false
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"content": "<extra_id_62>",
|
| 265 |
+
"lstrip": true,
|
| 266 |
+
"normalized": true,
|
| 267 |
+
"rstrip": false,
|
| 268 |
+
"single_word": false
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"content": "<extra_id_61>",
|
| 272 |
+
"lstrip": true,
|
| 273 |
+
"normalized": true,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"content": "<extra_id_60>",
|
| 279 |
+
"lstrip": true,
|
| 280 |
+
"normalized": true,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"content": "<extra_id_59>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"content": "<extra_id_58>",
|
| 293 |
+
"lstrip": true,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"content": "<extra_id_57>",
|
| 300 |
+
"lstrip": true,
|
| 301 |
+
"normalized": true,
|
| 302 |
+
"rstrip": false,
|
| 303 |
+
"single_word": false
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"content": "<extra_id_56>",
|
| 307 |
+
"lstrip": true,
|
| 308 |
+
"normalized": true,
|
| 309 |
+
"rstrip": false,
|
| 310 |
+
"single_word": false
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"content": "<extra_id_55>",
|
| 314 |
+
"lstrip": true,
|
| 315 |
+
"normalized": true,
|
| 316 |
+
"rstrip": false,
|
| 317 |
+
"single_word": false
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"content": "<extra_id_54>",
|
| 321 |
+
"lstrip": true,
|
| 322 |
+
"normalized": true,
|
| 323 |
+
"rstrip": false,
|
| 324 |
+
"single_word": false
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"content": "<extra_id_53>",
|
| 328 |
+
"lstrip": true,
|
| 329 |
+
"normalized": true,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"content": "<extra_id_52>",
|
| 335 |
+
"lstrip": true,
|
| 336 |
+
"normalized": true,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"content": "<extra_id_51>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": true,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"content": "<extra_id_50>",
|
| 349 |
+
"lstrip": true,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"content": "<extra_id_49>",
|
| 356 |
+
"lstrip": true,
|
| 357 |
+
"normalized": true,
|
| 358 |
+
"rstrip": false,
|
| 359 |
+
"single_word": false
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"content": "<extra_id_48>",
|
| 363 |
+
"lstrip": true,
|
| 364 |
+
"normalized": true,
|
| 365 |
+
"rstrip": false,
|
| 366 |
+
"single_word": false
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"content": "<extra_id_47>",
|
| 370 |
+
"lstrip": true,
|
| 371 |
+
"normalized": true,
|
| 372 |
+
"rstrip": false,
|
| 373 |
+
"single_word": false
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"content": "<extra_id_46>",
|
| 377 |
+
"lstrip": true,
|
| 378 |
+
"normalized": true,
|
| 379 |
+
"rstrip": false,
|
| 380 |
+
"single_word": false
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"content": "<extra_id_45>",
|
| 384 |
+
"lstrip": true,
|
| 385 |
+
"normalized": true,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"content": "<extra_id_44>",
|
| 391 |
+
"lstrip": true,
|
| 392 |
+
"normalized": true,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"content": "<extra_id_43>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": true,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"content": "<extra_id_42>",
|
| 405 |
+
"lstrip": true,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"content": "<extra_id_41>",
|
| 412 |
+
"lstrip": true,
|
| 413 |
+
"normalized": true,
|
| 414 |
+
"rstrip": false,
|
| 415 |
+
"single_word": false
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"content": "<extra_id_40>",
|
| 419 |
+
"lstrip": true,
|
| 420 |
+
"normalized": true,
|
| 421 |
+
"rstrip": false,
|
| 422 |
+
"single_word": false
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"content": "<extra_id_39>",
|
| 426 |
+
"lstrip": true,
|
| 427 |
+
"normalized": true,
|
| 428 |
+
"rstrip": false,
|
| 429 |
+
"single_word": false
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"content": "<extra_id_38>",
|
| 433 |
+
"lstrip": true,
|
| 434 |
+
"normalized": true,
|
| 435 |
+
"rstrip": false,
|
| 436 |
+
"single_word": false
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"content": "<extra_id_37>",
|
| 440 |
+
"lstrip": true,
|
| 441 |
+
"normalized": true,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"content": "<extra_id_36>",
|
| 447 |
+
"lstrip": true,
|
| 448 |
+
"normalized": true,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"content": "<extra_id_35>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": true,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"content": "<extra_id_34>",
|
| 461 |
+
"lstrip": true,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"content": "<extra_id_33>",
|
| 468 |
+
"lstrip": true,
|
| 469 |
+
"normalized": true,
|
| 470 |
+
"rstrip": false,
|
| 471 |
+
"single_word": false
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"content": "<extra_id_32>",
|
| 475 |
+
"lstrip": true,
|
| 476 |
+
"normalized": true,
|
| 477 |
+
"rstrip": false,
|
| 478 |
+
"single_word": false
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"content": "<extra_id_31>",
|
| 482 |
+
"lstrip": true,
|
| 483 |
+
"normalized": true,
|
| 484 |
+
"rstrip": false,
|
| 485 |
+
"single_word": false
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"content": "<extra_id_30>",
|
| 489 |
+
"lstrip": true,
|
| 490 |
+
"normalized": true,
|
| 491 |
+
"rstrip": false,
|
| 492 |
+
"single_word": false
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"content": "<extra_id_29>",
|
| 496 |
+
"lstrip": true,
|
| 497 |
+
"normalized": true,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"content": "<extra_id_28>",
|
| 503 |
+
"lstrip": true,
|
| 504 |
+
"normalized": true,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"content": "<extra_id_27>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": true,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"content": "<extra_id_26>",
|
| 517 |
+
"lstrip": true,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"content": "<extra_id_25>",
|
| 524 |
+
"lstrip": true,
|
| 525 |
+
"normalized": true,
|
| 526 |
+
"rstrip": false,
|
| 527 |
+
"single_word": false
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"content": "<extra_id_24>",
|
| 531 |
+
"lstrip": true,
|
| 532 |
+
"normalized": true,
|
| 533 |
+
"rstrip": false,
|
| 534 |
+
"single_word": false
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"content": "<extra_id_23>",
|
| 538 |
+
"lstrip": true,
|
| 539 |
+
"normalized": true,
|
| 540 |
+
"rstrip": false,
|
| 541 |
+
"single_word": false
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"content": "<extra_id_22>",
|
| 545 |
+
"lstrip": true,
|
| 546 |
+
"normalized": true,
|
| 547 |
+
"rstrip": false,
|
| 548 |
+
"single_word": false
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"content": "<extra_id_21>",
|
| 552 |
+
"lstrip": true,
|
| 553 |
+
"normalized": true,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"content": "<extra_id_20>",
|
| 559 |
+
"lstrip": true,
|
| 560 |
+
"normalized": true,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"content": "<extra_id_19>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": true,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"content": "<extra_id_18>",
|
| 573 |
+
"lstrip": true,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"content": "<extra_id_17>",
|
| 580 |
+
"lstrip": true,
|
| 581 |
+
"normalized": true,
|
| 582 |
+
"rstrip": false,
|
| 583 |
+
"single_word": false
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"content": "<extra_id_16>",
|
| 587 |
+
"lstrip": true,
|
| 588 |
+
"normalized": true,
|
| 589 |
+
"rstrip": false,
|
| 590 |
+
"single_word": false
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"content": "<extra_id_15>",
|
| 594 |
+
"lstrip": true,
|
| 595 |
+
"normalized": true,
|
| 596 |
+
"rstrip": false,
|
| 597 |
+
"single_word": false
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"content": "<extra_id_14>",
|
| 601 |
+
"lstrip": true,
|
| 602 |
+
"normalized": true,
|
| 603 |
+
"rstrip": false,
|
| 604 |
+
"single_word": false
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"content": "<extra_id_13>",
|
| 608 |
+
"lstrip": true,
|
| 609 |
+
"normalized": true,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"content": "<extra_id_12>",
|
| 615 |
+
"lstrip": true,
|
| 616 |
+
"normalized": true,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"content": "<extra_id_11>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": true,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"content": "<extra_id_10>",
|
| 629 |
+
"lstrip": true,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"content": "<extra_id_9>",
|
| 636 |
+
"lstrip": true,
|
| 637 |
+
"normalized": true,
|
| 638 |
+
"rstrip": false,
|
| 639 |
+
"single_word": false
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"content": "<extra_id_8>",
|
| 643 |
+
"lstrip": true,
|
| 644 |
+
"normalized": true,
|
| 645 |
+
"rstrip": false,
|
| 646 |
+
"single_word": false
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"content": "<extra_id_7>",
|
| 650 |
+
"lstrip": true,
|
| 651 |
+
"normalized": true,
|
| 652 |
+
"rstrip": false,
|
| 653 |
+
"single_word": false
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"content": "<extra_id_6>",
|
| 657 |
+
"lstrip": true,
|
| 658 |
+
"normalized": true,
|
| 659 |
+
"rstrip": false,
|
| 660 |
+
"single_word": false
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"content": "<extra_id_5>",
|
| 664 |
+
"lstrip": true,
|
| 665 |
+
"normalized": true,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"content": "<extra_id_4>",
|
| 671 |
+
"lstrip": true,
|
| 672 |
+
"normalized": true,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"content": "<extra_id_3>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": true,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"content": "<extra_id_2>",
|
| 685 |
+
"lstrip": true,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"content": "<extra_id_1>",
|
| 692 |
+
"lstrip": true,
|
| 693 |
+
"normalized": true,
|
| 694 |
+
"rstrip": false,
|
| 695 |
+
"single_word": false
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"content": "<extra_id_0>",
|
| 699 |
+
"lstrip": true,
|
| 700 |
+
"normalized": true,
|
| 701 |
+
"rstrip": false,
|
| 702 |
+
"single_word": false
|
| 703 |
+
}
|
| 704 |
+
],
|
| 705 |
+
"backend": "tokenizers",
|
| 706 |
+
"bos_token": "<s>",
|
| 707 |
+
"cls_token": "<s>",
|
| 708 |
+
"eos_token": "</s>",
|
| 709 |
+
"errors": "replace",
|
| 710 |
+
"extra_special_tokens": [],
|
| 711 |
+
"is_local": false,
|
| 712 |
+
"mask_token": "<mask>",
|
| 713 |
+
"model_max_length": 512,
|
| 714 |
+
"pad_token": "<pad>",
|
| 715 |
+
"sep_token": "</s>",
|
| 716 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 717 |
+
"trim_offsets": true,
|
| 718 |
+
"unk_token": "<unk>"
|
| 719 |
+
}
|
checkpoint-9213/trainer_state.json
ADDED
|
@@ -0,0 +1,1361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 9213,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0162813415825464,
|
| 14 |
+
"grad_norm": 3.7931034564971924,
|
| 15 |
+
"learning_rate": 4.975035276240096e-05,
|
| 16 |
+
"loss": 1.7502801513671875,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0325626831650928,
|
| 21 |
+
"grad_norm": 3.5913758277893066,
|
| 22 |
+
"learning_rate": 4.947899706935852e-05,
|
| 23 |
+
"loss": 0.8483324432373047,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04884402474763921,
|
| 28 |
+
"grad_norm": 3.3178822994232178,
|
| 29 |
+
"learning_rate": 4.9207641376316076e-05,
|
| 30 |
+
"loss": 0.5748957061767578,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0651253663301856,
|
| 35 |
+
"grad_norm": 2.392831802368164,
|
| 36 |
+
"learning_rate": 4.8936285683273635e-05,
|
| 37 |
+
"loss": 0.4335686492919922,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08140670791273201,
|
| 42 |
+
"grad_norm": 2.411132335662842,
|
| 43 |
+
"learning_rate": 4.8664929990231194e-05,
|
| 44 |
+
"loss": 0.45588829040527346,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09768804949527841,
|
| 49 |
+
"grad_norm": 3.383033275604248,
|
| 50 |
+
"learning_rate": 4.839357429718876e-05,
|
| 51 |
+
"loss": 0.38454761505126955,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11396939107782482,
|
| 56 |
+
"grad_norm": 1.5641525983810425,
|
| 57 |
+
"learning_rate": 4.812221860414632e-05,
|
| 58 |
+
"loss": 0.31118762969970704,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1302507326603712,
|
| 63 |
+
"grad_norm": 1.962287425994873,
|
| 64 |
+
"learning_rate": 4.785086291110388e-05,
|
| 65 |
+
"loss": 0.32715892791748047,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.14653207424291761,
|
| 70 |
+
"grad_norm": 2.539684534072876,
|
| 71 |
+
"learning_rate": 4.7579507218061436e-05,
|
| 72 |
+
"loss": 0.3269093704223633,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16281341582546402,
|
| 77 |
+
"grad_norm": 3.244333267211914,
|
| 78 |
+
"learning_rate": 4.7308151525018995e-05,
|
| 79 |
+
"loss": 0.2726271057128906,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.17909475740801042,
|
| 84 |
+
"grad_norm": 2.2011330127716064,
|
| 85 |
+
"learning_rate": 4.7036795831976553e-05,
|
| 86 |
+
"loss": 0.3161302185058594,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19537609899055683,
|
| 91 |
+
"grad_norm": 5.027646541595459,
|
| 92 |
+
"learning_rate": 4.676544013893412e-05,
|
| 93 |
+
"loss": 0.22250593185424805,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.21165744057310323,
|
| 98 |
+
"grad_norm": 0.6281399726867676,
|
| 99 |
+
"learning_rate": 4.649408444589168e-05,
|
| 100 |
+
"loss": 0.26152374267578127,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.22793878215564964,
|
| 105 |
+
"grad_norm": 3.362748622894287,
|
| 106 |
+
"learning_rate": 4.622272875284924e-05,
|
| 107 |
+
"loss": 0.2384391975402832,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24422012373819602,
|
| 112 |
+
"grad_norm": 0.9307177066802979,
|
| 113 |
+
"learning_rate": 4.5951373059806795e-05,
|
| 114 |
+
"loss": 0.19612070083618163,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2605014653207424,
|
| 119 |
+
"grad_norm": 3.107837438583374,
|
| 120 |
+
"learning_rate": 4.5680017366764354e-05,
|
| 121 |
+
"loss": 0.22400428771972655,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2767828069032888,
|
| 126 |
+
"grad_norm": 2.3350419998168945,
|
| 127 |
+
"learning_rate": 4.540866167372192e-05,
|
| 128 |
+
"loss": 0.246726131439209,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.29306414848583523,
|
| 133 |
+
"grad_norm": 1.3348891735076904,
|
| 134 |
+
"learning_rate": 4.513730598067948e-05,
|
| 135 |
+
"loss": 0.17960617065429688,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.30934549006838163,
|
| 140 |
+
"grad_norm": 1.4406858682632446,
|
| 141 |
+
"learning_rate": 4.486595028763704e-05,
|
| 142 |
+
"loss": 0.19865007400512696,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32562683165092804,
|
| 147 |
+
"grad_norm": 2.17195200920105,
|
| 148 |
+
"learning_rate": 4.4594594594594596e-05,
|
| 149 |
+
"loss": 0.19141647338867188,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.34190817323347444,
|
| 154 |
+
"grad_norm": 2.63667893409729,
|
| 155 |
+
"learning_rate": 4.4323238901552155e-05,
|
| 156 |
+
"loss": 0.1807699966430664,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.35818951481602085,
|
| 161 |
+
"grad_norm": 1.1883361339569092,
|
| 162 |
+
"learning_rate": 4.4051883208509714e-05,
|
| 163 |
+
"loss": 0.19377944946289063,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.37447085639856725,
|
| 168 |
+
"grad_norm": 0.6610957384109497,
|
| 169 |
+
"learning_rate": 4.378052751546728e-05,
|
| 170 |
+
"loss": 0.18130062103271485,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.39075219798111366,
|
| 175 |
+
"grad_norm": 1.802565336227417,
|
| 176 |
+
"learning_rate": 4.350917182242484e-05,
|
| 177 |
+
"loss": 0.17183830261230468,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.40703353956366006,
|
| 182 |
+
"grad_norm": 1.6211966276168823,
|
| 183 |
+
"learning_rate": 4.32378161293824e-05,
|
| 184 |
+
"loss": 0.1512114906311035,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.42331488114620647,
|
| 189 |
+
"grad_norm": 0.8947325944900513,
|
| 190 |
+
"learning_rate": 4.2966460436339956e-05,
|
| 191 |
+
"loss": 0.1733652877807617,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4395962227287529,
|
| 196 |
+
"grad_norm": 0.31800374388694763,
|
| 197 |
+
"learning_rate": 4.2695104743297515e-05,
|
| 198 |
+
"loss": 0.1839361572265625,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4558775643112993,
|
| 203 |
+
"grad_norm": 0.9736223220825195,
|
| 204 |
+
"learning_rate": 4.2423749050255074e-05,
|
| 205 |
+
"loss": 0.12980345726013184,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4721589058938456,
|
| 210 |
+
"grad_norm": 1.7321406602859497,
|
| 211 |
+
"learning_rate": 4.215239335721264e-05,
|
| 212 |
+
"loss": 0.14502116203308105,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48844024747639203,
|
| 217 |
+
"grad_norm": 0.47778311371803284,
|
| 218 |
+
"learning_rate": 4.18810376641702e-05,
|
| 219 |
+
"loss": 0.15735553741455077,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5047215890589385,
|
| 224 |
+
"grad_norm": 0.43138086795806885,
|
| 225 |
+
"learning_rate": 4.160968197112776e-05,
|
| 226 |
+
"loss": 0.13693093299865722,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5210029306414848,
|
| 231 |
+
"grad_norm": 0.7121404409408569,
|
| 232 |
+
"learning_rate": 4.1338326278085316e-05,
|
| 233 |
+
"loss": 0.13991880416870117,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5372842722240313,
|
| 238 |
+
"grad_norm": 1.8167650699615479,
|
| 239 |
+
"learning_rate": 4.1066970585042875e-05,
|
| 240 |
+
"loss": 0.13732372283935546,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5535656138065776,
|
| 245 |
+
"grad_norm": 1.801047921180725,
|
| 246 |
+
"learning_rate": 4.079561489200044e-05,
|
| 247 |
+
"loss": 0.1461949062347412,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5698469553891241,
|
| 252 |
+
"grad_norm": 1.2010151147842407,
|
| 253 |
+
"learning_rate": 4.0524259198958e-05,
|
| 254 |
+
"loss": 0.16667499542236328,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.5861282969716705,
|
| 259 |
+
"grad_norm": 0.31175410747528076,
|
| 260 |
+
"learning_rate": 4.025290350591556e-05,
|
| 261 |
+
"loss": 0.13411394119262696,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6024096385542169,
|
| 266 |
+
"grad_norm": 1.0062410831451416,
|
| 267 |
+
"learning_rate": 3.998154781287312e-05,
|
| 268 |
+
"loss": 0.141832914352417,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6186909801367633,
|
| 273 |
+
"grad_norm": 0.5772050619125366,
|
| 274 |
+
"learning_rate": 3.9710192119830675e-05,
|
| 275 |
+
"loss": 0.14646322250366212,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.6349723217193096,
|
| 280 |
+
"grad_norm": 1.1436623334884644,
|
| 281 |
+
"learning_rate": 3.9444263540649085e-05,
|
| 282 |
+
"loss": 0.11982306480407715,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6512536633018561,
|
| 287 |
+
"grad_norm": 0.6914354562759399,
|
| 288 |
+
"learning_rate": 3.9172907847606644e-05,
|
| 289 |
+
"loss": 0.13149891853332518,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6675350048844024,
|
| 294 |
+
"grad_norm": 0.5716465711593628,
|
| 295 |
+
"learning_rate": 3.89015521545642e-05,
|
| 296 |
+
"loss": 0.1392893123626709,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6838163464669489,
|
| 301 |
+
"grad_norm": 1.4796607494354248,
|
| 302 |
+
"learning_rate": 3.863019646152177e-05,
|
| 303 |
+
"loss": 0.1265252685546875,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7000976880494952,
|
| 308 |
+
"grad_norm": 0.849554717540741,
|
| 309 |
+
"learning_rate": 3.835884076847933e-05,
|
| 310 |
+
"loss": 0.1300504207611084,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.7163790296320417,
|
| 315 |
+
"grad_norm": 0.9229751825332642,
|
| 316 |
+
"learning_rate": 3.8087485075436886e-05,
|
| 317 |
+
"loss": 0.144088077545166,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.732660371214588,
|
| 322 |
+
"grad_norm": 0.6000483632087708,
|
| 323 |
+
"learning_rate": 3.7816129382394445e-05,
|
| 324 |
+
"loss": 0.1267460823059082,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7489417127971345,
|
| 329 |
+
"grad_norm": 1.584933876991272,
|
| 330 |
+
"learning_rate": 3.7544773689352004e-05,
|
| 331 |
+
"loss": 0.12461037635803222,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7652230543796809,
|
| 336 |
+
"grad_norm": 0.7694635987281799,
|
| 337 |
+
"learning_rate": 3.727341799630956e-05,
|
| 338 |
+
"loss": 0.1397037124633789,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.7815043959622273,
|
| 343 |
+
"grad_norm": 0.9538297653198242,
|
| 344 |
+
"learning_rate": 3.700206230326713e-05,
|
| 345 |
+
"loss": 0.09744812965393067,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7977857375447737,
|
| 350 |
+
"grad_norm": 1.10379159450531,
|
| 351 |
+
"learning_rate": 3.673070661022469e-05,
|
| 352 |
+
"loss": 0.14414773941040038,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8140670791273201,
|
| 357 |
+
"grad_norm": 1.6340835094451904,
|
| 358 |
+
"learning_rate": 3.6459350917182246e-05,
|
| 359 |
+
"loss": 0.11836291313171386,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8303484207098665,
|
| 364 |
+
"grad_norm": 0.06909910589456558,
|
| 365 |
+
"learning_rate": 3.6187995224139805e-05,
|
| 366 |
+
"loss": 0.13456206321716307,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.8466297622924129,
|
| 371 |
+
"grad_norm": 0.11458413302898407,
|
| 372 |
+
"learning_rate": 3.5916639531097364e-05,
|
| 373 |
+
"loss": 0.12975069046020507,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8629111038749593,
|
| 378 |
+
"grad_norm": 0.3121241331100464,
|
| 379 |
+
"learning_rate": 3.564528383805492e-05,
|
| 380 |
+
"loss": 0.10294739723205566,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.8791924454575057,
|
| 385 |
+
"grad_norm": 0.7833127975463867,
|
| 386 |
+
"learning_rate": 3.537392814501249e-05,
|
| 387 |
+
"loss": 0.1058332633972168,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.8954737870400521,
|
| 392 |
+
"grad_norm": 1.0220922231674194,
|
| 393 |
+
"learning_rate": 3.510257245197005e-05,
|
| 394 |
+
"loss": 0.11729028701782226,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.9117551286225986,
|
| 399 |
+
"grad_norm": 0.6296119093894958,
|
| 400 |
+
"learning_rate": 3.4831216758927606e-05,
|
| 401 |
+
"loss": 0.12148540496826171,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9280364702051449,
|
| 406 |
+
"grad_norm": 0.8129004240036011,
|
| 407 |
+
"learning_rate": 3.4559861065885164e-05,
|
| 408 |
+
"loss": 0.09763257980346679,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9443178117876913,
|
| 413 |
+
"grad_norm": 0.6814725399017334,
|
| 414 |
+
"learning_rate": 3.428850537284272e-05,
|
| 415 |
+
"loss": 0.10192323684692382,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9605991533702377,
|
| 420 |
+
"grad_norm": 0.19898249208927155,
|
| 421 |
+
"learning_rate": 3.401714967980029e-05,
|
| 422 |
+
"loss": 0.11552732467651367,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.9768804949527841,
|
| 427 |
+
"grad_norm": 0.7032152414321899,
|
| 428 |
+
"learning_rate": 3.374579398675785e-05,
|
| 429 |
+
"loss": 0.09218964576721192,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.9931618365353305,
|
| 434 |
+
"grad_norm": 0.5327423214912415,
|
| 435 |
+
"learning_rate": 3.3474438293715407e-05,
|
| 436 |
+
"loss": 0.11835557937622071,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.0,
|
| 441 |
+
"eval_bertscore_f1": 0.9908905607812545,
|
| 442 |
+
"eval_bleu": 0.8857676606120443,
|
| 443 |
+
"eval_loss": 0.08205162733793259,
|
| 444 |
+
"eval_meteor": 0.9292767478739071,
|
| 445 |
+
"eval_rouge1": 0.9454800565736884,
|
| 446 |
+
"eval_rouge2": 0.9108168851120266,
|
| 447 |
+
"eval_runtime": 61.8203,
|
| 448 |
+
"eval_samples_per_second": 20.899,
|
| 449 |
+
"eval_steps_per_second": 2.621,
|
| 450 |
+
"step": 3071
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.009443178117877,
|
| 454 |
+
"grad_norm": 0.7608644366264343,
|
| 455 |
+
"learning_rate": 3.3203082600672965e-05,
|
| 456 |
+
"loss": 0.08838626861572266,
|
| 457 |
+
"step": 3100
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0257245197004232,
|
| 461 |
+
"grad_norm": 0.6126351952552795,
|
| 462 |
+
"learning_rate": 3.2931726907630524e-05,
|
| 463 |
+
"loss": 0.07393273830413818,
|
| 464 |
+
"step": 3150
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.0420058612829697,
|
| 468 |
+
"grad_norm": 0.9907364845275879,
|
| 469 |
+
"learning_rate": 3.266037121458808e-05,
|
| 470 |
+
"loss": 0.1005620002746582,
|
| 471 |
+
"step": 3200
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.0582872028655161,
|
| 475 |
+
"grad_norm": 1.0079267024993896,
|
| 476 |
+
"learning_rate": 3.238901552154565e-05,
|
| 477 |
+
"loss": 0.0909033203125,
|
| 478 |
+
"step": 3250
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.0745685444480626,
|
| 482 |
+
"grad_norm": 1.661521315574646,
|
| 483 |
+
"learning_rate": 3.211765982850321e-05,
|
| 484 |
+
"loss": 0.07444488525390625,
|
| 485 |
+
"step": 3300
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.0908498860306088,
|
| 489 |
+
"grad_norm": 0.5184240341186523,
|
| 490 |
+
"learning_rate": 3.1846304135460766e-05,
|
| 491 |
+
"loss": 0.08309778213500976,
|
| 492 |
+
"step": 3350
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1071312276131553,
|
| 496 |
+
"grad_norm": 1.1483348608016968,
|
| 497 |
+
"learning_rate": 3.1574948442418325e-05,
|
| 498 |
+
"loss": 0.07855434417724609,
|
| 499 |
+
"step": 3400
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1234125691957018,
|
| 503 |
+
"grad_norm": 1.0581797361373901,
|
| 504 |
+
"learning_rate": 3.1303592749375884e-05,
|
| 505 |
+
"loss": 0.0779510498046875,
|
| 506 |
+
"step": 3450
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1396939107782482,
|
| 510 |
+
"grad_norm": 0.3960680663585663,
|
| 511 |
+
"learning_rate": 3.103223705633344e-05,
|
| 512 |
+
"loss": 0.07558696269989014,
|
| 513 |
+
"step": 3500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.1559752523607945,
|
| 517 |
+
"grad_norm": 0.7705583572387695,
|
| 518 |
+
"learning_rate": 3.076088136329101e-05,
|
| 519 |
+
"loss": 0.07015891551971436,
|
| 520 |
+
"step": 3550
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.172256593943341,
|
| 524 |
+
"grad_norm": 0.9814662933349609,
|
| 525 |
+
"learning_rate": 3.0489525670248564e-05,
|
| 526 |
+
"loss": 0.09184465408325196,
|
| 527 |
+
"step": 3600
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.1885379355258874,
|
| 531 |
+
"grad_norm": 0.16037984192371368,
|
| 532 |
+
"learning_rate": 3.0218169977206123e-05,
|
| 533 |
+
"loss": 0.10087477684020996,
|
| 534 |
+
"step": 3650
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2048192771084336,
|
| 538 |
+
"grad_norm": 0.4658585488796234,
|
| 539 |
+
"learning_rate": 2.994681428416368e-05,
|
| 540 |
+
"loss": 0.0878927993774414,
|
| 541 |
+
"step": 3700
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.22110061869098,
|
| 545 |
+
"grad_norm": 0.6178460717201233,
|
| 546 |
+
"learning_rate": 2.967545859112124e-05,
|
| 547 |
+
"loss": 0.08248810768127442,
|
| 548 |
+
"step": 3750
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2373819602735265,
|
| 552 |
+
"grad_norm": 0.8095784783363342,
|
| 553 |
+
"learning_rate": 2.9404102898078806e-05,
|
| 554 |
+
"loss": 0.07741629600524902,
|
| 555 |
+
"step": 3800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.253663301856073,
|
| 559 |
+
"grad_norm": 0.7121015191078186,
|
| 560 |
+
"learning_rate": 2.9132747205036365e-05,
|
| 561 |
+
"loss": 0.06926633358001709,
|
| 562 |
+
"step": 3850
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2699446434386195,
|
| 566 |
+
"grad_norm": 0.9626070857048035,
|
| 567 |
+
"learning_rate": 2.8861391511993923e-05,
|
| 568 |
+
"loss": 0.08737580299377441,
|
| 569 |
+
"step": 3900
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.2862259850211657,
|
| 573 |
+
"grad_norm": 1.617689847946167,
|
| 574 |
+
"learning_rate": 2.8590035818951482e-05,
|
| 575 |
+
"loss": 0.08954649925231933,
|
| 576 |
+
"step": 3950
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.3025073266037122,
|
| 580 |
+
"grad_norm": 0.17025412619113922,
|
| 581 |
+
"learning_rate": 2.831868012590904e-05,
|
| 582 |
+
"loss": 0.07303418159484863,
|
| 583 |
+
"step": 4000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.3187886681862586,
|
| 587 |
+
"grad_norm": 0.8474647402763367,
|
| 588 |
+
"learning_rate": 2.80473244328666e-05,
|
| 589 |
+
"loss": 0.10014421463012696,
|
| 590 |
+
"step": 4050
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3350700097688049,
|
| 594 |
+
"grad_norm": 1.1335641145706177,
|
| 595 |
+
"learning_rate": 2.7775968739824165e-05,
|
| 596 |
+
"loss": 0.09378931999206543,
|
| 597 |
+
"step": 4100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.3513513513513513,
|
| 601 |
+
"grad_norm": 0.05914885550737381,
|
| 602 |
+
"learning_rate": 2.7504613046781724e-05,
|
| 603 |
+
"loss": 0.0685378360748291,
|
| 604 |
+
"step": 4150
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3676326929338978,
|
| 608 |
+
"grad_norm": 0.49404996633529663,
|
| 609 |
+
"learning_rate": 2.7233257353739283e-05,
|
| 610 |
+
"loss": 0.0691972017288208,
|
| 611 |
+
"step": 4200
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.3839140345164442,
|
| 615 |
+
"grad_norm": 0.49692803621292114,
|
| 616 |
+
"learning_rate": 2.6961901660696842e-05,
|
| 617 |
+
"loss": 0.07013116836547852,
|
| 618 |
+
"step": 4250
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.4001953760989905,
|
| 622 |
+
"grad_norm": 1.2489663362503052,
|
| 623 |
+
"learning_rate": 2.66905459676544e-05,
|
| 624 |
+
"loss": 0.06815986156463623,
|
| 625 |
+
"step": 4300
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.416476717681537,
|
| 629 |
+
"grad_norm": 1.234505534172058,
|
| 630 |
+
"learning_rate": 2.641919027461196e-05,
|
| 631 |
+
"loss": 0.07438003540039062,
|
| 632 |
+
"step": 4350
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.4327580592640834,
|
| 636 |
+
"grad_norm": 0.5595135688781738,
|
| 637 |
+
"learning_rate": 2.6147834581569525e-05,
|
| 638 |
+
"loss": 0.08010281562805176,
|
| 639 |
+
"step": 4400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.4490394008466296,
|
| 643 |
+
"grad_norm": 0.713994026184082,
|
| 644 |
+
"learning_rate": 2.5876478888527084e-05,
|
| 645 |
+
"loss": 0.08089996337890625,
|
| 646 |
+
"step": 4450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.465320742429176,
|
| 650 |
+
"grad_norm": 0.41522467136383057,
|
| 651 |
+
"learning_rate": 2.5605123195484643e-05,
|
| 652 |
+
"loss": 0.07183042049407959,
|
| 653 |
+
"step": 4500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.4816020840117226,
|
| 657 |
+
"grad_norm": 0.4079296290874481,
|
| 658 |
+
"learning_rate": 2.53337675024422e-05,
|
| 659 |
+
"loss": 0.07589399337768554,
|
| 660 |
+
"step": 4550
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.497883425594269,
|
| 664 |
+
"grad_norm": 0.3075660169124603,
|
| 665 |
+
"learning_rate": 2.506241180939976e-05,
|
| 666 |
+
"loss": 0.07919666767120362,
|
| 667 |
+
"step": 4600
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.5141647671768155,
|
| 671 |
+
"grad_norm": 1.5832964181900024,
|
| 672 |
+
"learning_rate": 2.4791056116357323e-05,
|
| 673 |
+
"loss": 0.06133227825164795,
|
| 674 |
+
"step": 4650
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.530446108759362,
|
| 678 |
+
"grad_norm": 0.32941189408302307,
|
| 679 |
+
"learning_rate": 2.451970042331488e-05,
|
| 680 |
+
"loss": 0.07278666496276856,
|
| 681 |
+
"step": 4700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5467274503419082,
|
| 685 |
+
"grad_norm": 0.5237034559249878,
|
| 686 |
+
"learning_rate": 2.4248344730272444e-05,
|
| 687 |
+
"loss": 0.07373996734619141,
|
| 688 |
+
"step": 4750
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.5630087919244544,
|
| 692 |
+
"grad_norm": 0.056225214153528214,
|
| 693 |
+
"learning_rate": 2.3976989037230003e-05,
|
| 694 |
+
"loss": 0.08032115936279297,
|
| 695 |
+
"step": 4800
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.5792901335070009,
|
| 699 |
+
"grad_norm": 0.6325415372848511,
|
| 700 |
+
"learning_rate": 2.370563334418756e-05,
|
| 701 |
+
"loss": 0.08559741973876953,
|
| 702 |
+
"step": 4850
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.5955714750895473,
|
| 706 |
+
"grad_norm": 1.230356216430664,
|
| 707 |
+
"learning_rate": 2.3434277651145124e-05,
|
| 708 |
+
"loss": 0.07180691242218018,
|
| 709 |
+
"step": 4900
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.6118528166720938,
|
| 713 |
+
"grad_norm": 3.57700252532959,
|
| 714 |
+
"learning_rate": 2.3162921958102682e-05,
|
| 715 |
+
"loss": 0.06951488494873047,
|
| 716 |
+
"step": 4950
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.6281341582546403,
|
| 720 |
+
"grad_norm": 1.004461646080017,
|
| 721 |
+
"learning_rate": 2.289156626506024e-05,
|
| 722 |
+
"loss": 0.057218775749206544,
|
| 723 |
+
"step": 5000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6444154998371867,
|
| 727 |
+
"grad_norm": 0.44509896636009216,
|
| 728 |
+
"learning_rate": 2.2620210572017803e-05,
|
| 729 |
+
"loss": 0.08383867263793945,
|
| 730 |
+
"step": 5050
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.660696841419733,
|
| 734 |
+
"grad_norm": 0.6665693521499634,
|
| 735 |
+
"learning_rate": 2.2348854878975362e-05,
|
| 736 |
+
"loss": 0.0708467960357666,
|
| 737 |
+
"step": 5100
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.6769781830022794,
|
| 741 |
+
"grad_norm": 0.520028293132782,
|
| 742 |
+
"learning_rate": 2.207749918593292e-05,
|
| 743 |
+
"loss": 0.07018136024475098,
|
| 744 |
+
"step": 5150
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.6932595245848256,
|
| 748 |
+
"grad_norm": 0.7581444382667542,
|
| 749 |
+
"learning_rate": 2.1806143492890483e-05,
|
| 750 |
+
"loss": 0.06788209915161132,
|
| 751 |
+
"step": 5200
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.709540866167372,
|
| 755 |
+
"grad_norm": 0.34040266275405884,
|
| 756 |
+
"learning_rate": 2.1534787799848042e-05,
|
| 757 |
+
"loss": 0.08334577560424805,
|
| 758 |
+
"step": 5250
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.7258222077499186,
|
| 762 |
+
"grad_norm": 0.5161302089691162,
|
| 763 |
+
"learning_rate": 2.1263432106805604e-05,
|
| 764 |
+
"loss": 0.06911201477050781,
|
| 765 |
+
"step": 5300
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.742103549332465,
|
| 769 |
+
"grad_norm": 0.8025581240653992,
|
| 770 |
+
"learning_rate": 2.0992076413763163e-05,
|
| 771 |
+
"loss": 0.06495306968688964,
|
| 772 |
+
"step": 5350
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.7583848909150115,
|
| 776 |
+
"grad_norm": 1.0504302978515625,
|
| 777 |
+
"learning_rate": 2.0720720720720722e-05,
|
| 778 |
+
"loss": 0.06523369789123536,
|
| 779 |
+
"step": 5400
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.774666232497558,
|
| 783 |
+
"grad_norm": 1.5722064971923828,
|
| 784 |
+
"learning_rate": 2.0449365027678284e-05,
|
| 785 |
+
"loss": 0.06998776435852051,
|
| 786 |
+
"step": 5450
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.7909475740801042,
|
| 790 |
+
"grad_norm": 1.4498728513717651,
|
| 791 |
+
"learning_rate": 2.0178009334635843e-05,
|
| 792 |
+
"loss": 0.07263383388519287,
|
| 793 |
+
"step": 5500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.8072289156626506,
|
| 797 |
+
"grad_norm": 0.1697084903717041,
|
| 798 |
+
"learning_rate": 1.9906653641593402e-05,
|
| 799 |
+
"loss": 0.06083515644073487,
|
| 800 |
+
"step": 5550
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8235102572451969,
|
| 804 |
+
"grad_norm": 0.043431248515844345,
|
| 805 |
+
"learning_rate": 1.9635297948550964e-05,
|
| 806 |
+
"loss": 0.0591968297958374,
|
| 807 |
+
"step": 5600
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8397915988277433,
|
| 811 |
+
"grad_norm": 0.9290309548377991,
|
| 812 |
+
"learning_rate": 1.9363942255508523e-05,
|
| 813 |
+
"loss": 0.060645227432250974,
|
| 814 |
+
"step": 5650
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.8560729404102898,
|
| 818 |
+
"grad_norm": 1.0422381162643433,
|
| 819 |
+
"learning_rate": 1.9092586562466082e-05,
|
| 820 |
+
"loss": 0.07442611217498779,
|
| 821 |
+
"step": 5700
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8723542819928363,
|
| 825 |
+
"grad_norm": 0.3466901183128357,
|
| 826 |
+
"learning_rate": 1.8821230869423644e-05,
|
| 827 |
+
"loss": 0.07767025470733642,
|
| 828 |
+
"step": 5750
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.8886356235753827,
|
| 832 |
+
"grad_norm": 0.39657458662986755,
|
| 833 |
+
"learning_rate": 1.8549875176381203e-05,
|
| 834 |
+
"loss": 0.06347317218780518,
|
| 835 |
+
"step": 5800
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.904916965157929,
|
| 839 |
+
"grad_norm": 1.00450599193573,
|
| 840 |
+
"learning_rate": 1.827851948333876e-05,
|
| 841 |
+
"loss": 0.06967205524444581,
|
| 842 |
+
"step": 5850
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.9211983067404754,
|
| 846 |
+
"grad_norm": 1.1727004051208496,
|
| 847 |
+
"learning_rate": 1.800716379029632e-05,
|
| 848 |
+
"loss": 0.06747759819030762,
|
| 849 |
+
"step": 5900
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.9374796483230217,
|
| 853 |
+
"grad_norm": 0.8829087615013123,
|
| 854 |
+
"learning_rate": 1.7735808097253883e-05,
|
| 855 |
+
"loss": 0.07414731979370118,
|
| 856 |
+
"step": 5950
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.9537609899055681,
|
| 860 |
+
"grad_norm": 1.3967463970184326,
|
| 861 |
+
"learning_rate": 1.746445240421144e-05,
|
| 862 |
+
"loss": 0.06446901321411133,
|
| 863 |
+
"step": 6000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.9700423314881146,
|
| 867 |
+
"grad_norm": 0.9375430345535278,
|
| 868 |
+
"learning_rate": 1.7193096711169e-05,
|
| 869 |
+
"loss": 0.06800864696502686,
|
| 870 |
+
"step": 6050
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.986323673070661,
|
| 874 |
+
"grad_norm": 0.9516276717185974,
|
| 875 |
+
"learning_rate": 1.692174101812656e-05,
|
| 876 |
+
"loss": 0.08866607666015625,
|
| 877 |
+
"step": 6100
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.0,
|
| 881 |
+
"eval_bertscore_f1": 0.9923369143584934,
|
| 882 |
+
"eval_bleu": 0.8956281706064034,
|
| 883 |
+
"eval_loss": 0.06535279005765915,
|
| 884 |
+
"eval_meteor": 0.938086576675145,
|
| 885 |
+
"eval_rouge1": 0.950788798151768,
|
| 886 |
+
"eval_rouge2": 0.9176212368118313,
|
| 887 |
+
"eval_runtime": 58.3038,
|
| 888 |
+
"eval_samples_per_second": 22.16,
|
| 889 |
+
"eval_steps_per_second": 2.779,
|
| 890 |
+
"step": 6142
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.0026050146532075,
|
| 894 |
+
"grad_norm": 0.3171500861644745,
|
| 895 |
+
"learning_rate": 1.665038532508412e-05,
|
| 896 |
+
"loss": 0.06093011379241944,
|
| 897 |
+
"step": 6150
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.018886356235754,
|
| 901 |
+
"grad_norm": 0.3844246566295624,
|
| 902 |
+
"learning_rate": 1.637902963204168e-05,
|
| 903 |
+
"loss": 0.05403701782226562,
|
| 904 |
+
"step": 6200
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.0351676978183004,
|
| 908 |
+
"grad_norm": 1.5091606378555298,
|
| 909 |
+
"learning_rate": 1.610767393899924e-05,
|
| 910 |
+
"loss": 0.06063016414642334,
|
| 911 |
+
"step": 6250
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.0514490394008464,
|
| 915 |
+
"grad_norm": 0.5060765743255615,
|
| 916 |
+
"learning_rate": 1.58363182459568e-05,
|
| 917 |
+
"loss": 0.06424860954284668,
|
| 918 |
+
"step": 6300
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.067730380983393,
|
| 922 |
+
"grad_norm": 0.5501185059547424,
|
| 923 |
+
"learning_rate": 1.556496255291436e-05,
|
| 924 |
+
"loss": 0.052588853836059574,
|
| 925 |
+
"step": 6350
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 2.0840117225659394,
|
| 929 |
+
"grad_norm": 0.5140529274940491,
|
| 930 |
+
"learning_rate": 1.529360685987192e-05,
|
| 931 |
+
"loss": 0.05470933437347412,
|
| 932 |
+
"step": 6400
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.100293064148486,
|
| 936 |
+
"grad_norm": 0.13059721887111664,
|
| 937 |
+
"learning_rate": 1.5022251166829483e-05,
|
| 938 |
+
"loss": 0.05880857944488525,
|
| 939 |
+
"step": 6450
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.1165744057310323,
|
| 943 |
+
"grad_norm": 0.5545864701271057,
|
| 944 |
+
"learning_rate": 1.4750895473787041e-05,
|
| 945 |
+
"loss": 0.05454400062561035,
|
| 946 |
+
"step": 6500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.1328557473135787,
|
| 950 |
+
"grad_norm": 0.7566473484039307,
|
| 951 |
+
"learning_rate": 1.44795397807446e-05,
|
| 952 |
+
"loss": 0.05996315956115723,
|
| 953 |
+
"step": 6550
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.149137088896125,
|
| 957 |
+
"grad_norm": 0.6309687495231628,
|
| 958 |
+
"learning_rate": 1.420818408770216e-05,
|
| 959 |
+
"loss": 0.06270824909210206,
|
| 960 |
+
"step": 6600
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.165418430478671,
|
| 964 |
+
"grad_norm": 0.6882494688034058,
|
| 965 |
+
"learning_rate": 1.3936828394659721e-05,
|
| 966 |
+
"loss": 0.0579791259765625,
|
| 967 |
+
"step": 6650
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.1816997720612177,
|
| 971 |
+
"grad_norm": 0.5102435946464539,
|
| 972 |
+
"learning_rate": 1.366547270161728e-05,
|
| 973 |
+
"loss": 0.05909278869628906,
|
| 974 |
+
"step": 6700
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.197981113643764,
|
| 978 |
+
"grad_norm": 0.5612519979476929,
|
| 979 |
+
"learning_rate": 1.339411700857484e-05,
|
| 980 |
+
"loss": 0.0631598711013794,
|
| 981 |
+
"step": 6750
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.2142624552263106,
|
| 985 |
+
"grad_norm": 0.5335197448730469,
|
| 986 |
+
"learning_rate": 1.31227613155324e-05,
|
| 987 |
+
"loss": 0.061668686866760254,
|
| 988 |
+
"step": 6800
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.230543796808857,
|
| 992 |
+
"grad_norm": 0.26907965540885925,
|
| 993 |
+
"learning_rate": 1.285140562248996e-05,
|
| 994 |
+
"loss": 0.05813938617706299,
|
| 995 |
+
"step": 6850
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 2.2468251383914035,
|
| 999 |
+
"grad_norm": 0.9871731996536255,
|
| 1000 |
+
"learning_rate": 1.258004992944752e-05,
|
| 1001 |
+
"loss": 0.06166846752166748,
|
| 1002 |
+
"step": 6900
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.26310647997395,
|
| 1006 |
+
"grad_norm": 0.7092576622962952,
|
| 1007 |
+
"learning_rate": 1.230869423640508e-05,
|
| 1008 |
+
"loss": 0.05214274883270264,
|
| 1009 |
+
"step": 6950
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.2793878215564964,
|
| 1013 |
+
"grad_norm": 0.6084023714065552,
|
| 1014 |
+
"learning_rate": 1.203733854336264e-05,
|
| 1015 |
+
"loss": 0.06180807590484619,
|
| 1016 |
+
"step": 7000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.295669163139043,
|
| 1020 |
+
"grad_norm": 1.0545355081558228,
|
| 1021 |
+
"learning_rate": 1.17659828503202e-05,
|
| 1022 |
+
"loss": 0.05810202598571777,
|
| 1023 |
+
"step": 7050
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.311950504721589,
|
| 1027 |
+
"grad_norm": 0.9563855528831482,
|
| 1028 |
+
"learning_rate": 1.149462715727776e-05,
|
| 1029 |
+
"loss": 0.05618003368377686,
|
| 1030 |
+
"step": 7100
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.3282318463041354,
|
| 1034 |
+
"grad_norm": 0.6173250079154968,
|
| 1035 |
+
"learning_rate": 1.122327146423532e-05,
|
| 1036 |
+
"loss": 0.06320930480957031,
|
| 1037 |
+
"step": 7150
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.344513187886682,
|
| 1041 |
+
"grad_norm": 0.08047935366630554,
|
| 1042 |
+
"learning_rate": 1.095191577119288e-05,
|
| 1043 |
+
"loss": 0.058518905639648434,
|
| 1044 |
+
"step": 7200
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.3607945294692283,
|
| 1048 |
+
"grad_norm": 0.6877385973930359,
|
| 1049 |
+
"learning_rate": 1.0680560078150439e-05,
|
| 1050 |
+
"loss": 0.07214242458343506,
|
| 1051 |
+
"step": 7250
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.3770758710517748,
|
| 1055 |
+
"grad_norm": 0.7921647429466248,
|
| 1056 |
+
"learning_rate": 1.0409204385108e-05,
|
| 1057 |
+
"loss": 0.0554658842086792,
|
| 1058 |
+
"step": 7300
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.393357212634321,
|
| 1062 |
+
"grad_norm": 0.23214460909366608,
|
| 1063 |
+
"learning_rate": 1.013784869206556e-05,
|
| 1064 |
+
"loss": 0.05945809364318848,
|
| 1065 |
+
"step": 7350
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.4096385542168672,
|
| 1069 |
+
"grad_norm": 0.23501083254814148,
|
| 1070 |
+
"learning_rate": 9.86649299902312e-06,
|
| 1071 |
+
"loss": 0.04184418678283691,
|
| 1072 |
+
"step": 7400
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.4259198957994137,
|
| 1076 |
+
"grad_norm": 0.19243040680885315,
|
| 1077 |
+
"learning_rate": 9.59513730598068e-06,
|
| 1078 |
+
"loss": 0.0685301399230957,
|
| 1079 |
+
"step": 7450
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.44220123738196,
|
| 1083 |
+
"grad_norm": 0.03571745380759239,
|
| 1084 |
+
"learning_rate": 9.32378161293824e-06,
|
| 1085 |
+
"loss": 0.05060723781585694,
|
| 1086 |
+
"step": 7500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.4584825789645066,
|
| 1090 |
+
"grad_norm": 0.06310860812664032,
|
| 1091 |
+
"learning_rate": 9.0524259198958e-06,
|
| 1092 |
+
"loss": 0.06717358589172363,
|
| 1093 |
+
"step": 7550
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 2.474763920547053,
|
| 1097 |
+
"grad_norm": 0.4403184950351715,
|
| 1098 |
+
"learning_rate": 8.78107022685336e-06,
|
| 1099 |
+
"loss": 0.0508097505569458,
|
| 1100 |
+
"step": 7600
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 2.4910452621295995,
|
| 1104 |
+
"grad_norm": 0.1725953370332718,
|
| 1105 |
+
"learning_rate": 8.50971453381092e-06,
|
| 1106 |
+
"loss": 0.06436698913574218,
|
| 1107 |
+
"step": 7650
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 2.507326603712146,
|
| 1111 |
+
"grad_norm": 0.560205340385437,
|
| 1112 |
+
"learning_rate": 8.23835884076848e-06,
|
| 1113 |
+
"loss": 0.05466559410095215,
|
| 1114 |
+
"step": 7700
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.5236079452946925,
|
| 1118 |
+
"grad_norm": 0.8589635491371155,
|
| 1119 |
+
"learning_rate": 7.96700314772604e-06,
|
| 1120 |
+
"loss": 0.052462191581726075,
|
| 1121 |
+
"step": 7750
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.539889286877239,
|
| 1125 |
+
"grad_norm": 0.40856632590293884,
|
| 1126 |
+
"learning_rate": 7.6956474546836e-06,
|
| 1127 |
+
"loss": 0.057110257148742676,
|
| 1128 |
+
"step": 7800
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.556170628459785,
|
| 1132 |
+
"grad_norm": 0.2351612001657486,
|
| 1133 |
+
"learning_rate": 7.424291761641159e-06,
|
| 1134 |
+
"loss": 0.049067635536193845,
|
| 1135 |
+
"step": 7850
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.5724519700423314,
|
| 1139 |
+
"grad_norm": 0.3204529583454132,
|
| 1140 |
+
"learning_rate": 7.15293606859872e-06,
|
| 1141 |
+
"loss": 0.049645824432373045,
|
| 1142 |
+
"step": 7900
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 2.588733311624878,
|
| 1146 |
+
"grad_norm": 0.43326708674430847,
|
| 1147 |
+
"learning_rate": 6.881580375556279e-06,
|
| 1148 |
+
"loss": 0.050102224349975584,
|
| 1149 |
+
"step": 7950
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.6050146532074243,
|
| 1153 |
+
"grad_norm": 1.065234899520874,
|
| 1154 |
+
"learning_rate": 6.610224682513839e-06,
|
| 1155 |
+
"loss": 0.06275768280029297,
|
| 1156 |
+
"step": 8000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.6212959947899708,
|
| 1160 |
+
"grad_norm": 0.26160168647766113,
|
| 1161 |
+
"learning_rate": 6.3388689894714e-06,
|
| 1162 |
+
"loss": 0.04881012439727783,
|
| 1163 |
+
"step": 8050
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 2.6375773363725172,
|
| 1167 |
+
"grad_norm": 0.6686789989471436,
|
| 1168 |
+
"learning_rate": 6.067513296428959e-06,
|
| 1169 |
+
"loss": 0.058712401390075684,
|
| 1170 |
+
"step": 8100
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.6538586779550632,
|
| 1174 |
+
"grad_norm": 0.4735671281814575,
|
| 1175 |
+
"learning_rate": 5.796157603386519e-06,
|
| 1176 |
+
"loss": 0.05793766498565674,
|
| 1177 |
+
"step": 8150
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.6701400195376097,
|
| 1181 |
+
"grad_norm": 0.9112767577171326,
|
| 1182 |
+
"learning_rate": 5.5248019103440796e-06,
|
| 1183 |
+
"loss": 0.05646980285644531,
|
| 1184 |
+
"step": 8200
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.686421361120156,
|
| 1188 |
+
"grad_norm": 0.3665359914302826,
|
| 1189 |
+
"learning_rate": 5.253446217301639e-06,
|
| 1190 |
+
"loss": 0.05863104820251465,
|
| 1191 |
+
"step": 8250
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.7027027027027026,
|
| 1195 |
+
"grad_norm": 0.39087387919425964,
|
| 1196 |
+
"learning_rate": 4.982090524259199e-06,
|
| 1197 |
+
"loss": 0.04811685085296631,
|
| 1198 |
+
"step": 8300
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.718984044285249,
|
| 1202 |
+
"grad_norm": 0.7103152871131897,
|
| 1203 |
+
"learning_rate": 4.7107348312167594e-06,
|
| 1204 |
+
"loss": 0.0660721492767334,
|
| 1205 |
+
"step": 8350
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.7352653858677956,
|
| 1209 |
+
"grad_norm": 0.30644118785858154,
|
| 1210 |
+
"learning_rate": 4.439379138174319e-06,
|
| 1211 |
+
"loss": 0.061232595443725585,
|
| 1212 |
+
"step": 8400
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 2.751546727450342,
|
| 1216 |
+
"grad_norm": 0.6912480592727661,
|
| 1217 |
+
"learning_rate": 4.16802344513188e-06,
|
| 1218 |
+
"loss": 0.0465062952041626,
|
| 1219 |
+
"step": 8450
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 2.7678280690328885,
|
| 1223 |
+
"grad_norm": 0.2372223436832428,
|
| 1224 |
+
"learning_rate": 3.896667752089439e-06,
|
| 1225 |
+
"loss": 0.05613251686096191,
|
| 1226 |
+
"step": 8500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 2.784109410615435,
|
| 1230 |
+
"grad_norm": 0.3588544428348541,
|
| 1231 |
+
"learning_rate": 3.6253120590469985e-06,
|
| 1232 |
+
"loss": 0.06228278636932373,
|
| 1233 |
+
"step": 8550
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.800390752197981,
|
| 1237 |
+
"grad_norm": 0.8760668039321899,
|
| 1238 |
+
"learning_rate": 3.353956366004559e-06,
|
| 1239 |
+
"loss": 0.058021135330200195,
|
| 1240 |
+
"step": 8600
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 2.8166720937805274,
|
| 1244 |
+
"grad_norm": 0.39105167984962463,
|
| 1245 |
+
"learning_rate": 3.0826006729621187e-06,
|
| 1246 |
+
"loss": 0.05042066097259521,
|
| 1247 |
+
"step": 8650
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 2.832953435363074,
|
| 1251 |
+
"grad_norm": 0.8453779816627502,
|
| 1252 |
+
"learning_rate": 2.811244979919679e-06,
|
| 1253 |
+
"loss": 0.05310141086578369,
|
| 1254 |
+
"step": 8700
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.8492347769456203,
|
| 1258 |
+
"grad_norm": 0.3931414484977722,
|
| 1259 |
+
"learning_rate": 2.539889286877239e-06,
|
| 1260 |
+
"loss": 0.04613284111022949,
|
| 1261 |
+
"step": 8750
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.865516118528167,
|
| 1265 |
+
"grad_norm": 0.601372480392456,
|
| 1266 |
+
"learning_rate": 2.268533593834799e-06,
|
| 1267 |
+
"loss": 0.055337414741516114,
|
| 1268 |
+
"step": 8800
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 2.8817974601107132,
|
| 1272 |
+
"grad_norm": 0.40091976523399353,
|
| 1273 |
+
"learning_rate": 1.9971779007923587e-06,
|
| 1274 |
+
"loss": 0.05075720310211182,
|
| 1275 |
+
"step": 8850
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.8980788016932593,
|
| 1279 |
+
"grad_norm": 0.9332064986228943,
|
| 1280 |
+
"learning_rate": 1.7258222077499185e-06,
|
| 1281 |
+
"loss": 0.04717796325683594,
|
| 1282 |
+
"step": 8900
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 2.9143601432758057,
|
| 1286 |
+
"grad_norm": 0.7941976189613342,
|
| 1287 |
+
"learning_rate": 1.4544665147074786e-06,
|
| 1288 |
+
"loss": 0.07562547206878661,
|
| 1289 |
+
"step": 8950
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.930641484858352,
|
| 1293 |
+
"grad_norm": 0.6598140597343445,
|
| 1294 |
+
"learning_rate": 1.1831108216650385e-06,
|
| 1295 |
+
"loss": 0.05916054248809814,
|
| 1296 |
+
"step": 9000
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.9469228264408986,
|
| 1300 |
+
"grad_norm": 0.07086297869682312,
|
| 1301 |
+
"learning_rate": 9.117551286225986e-07,
|
| 1302 |
+
"loss": 0.05104278087615967,
|
| 1303 |
+
"step": 9050
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 2.963204168023445,
|
| 1307 |
+
"grad_norm": 0.5035263299942017,
|
| 1308 |
+
"learning_rate": 6.403994355801585e-07,
|
| 1309 |
+
"loss": 0.04357606887817383,
|
| 1310 |
+
"step": 9100
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 2.9794855096059916,
|
| 1314 |
+
"grad_norm": 0.28602153062820435,
|
| 1315 |
+
"learning_rate": 3.690437425377185e-07,
|
| 1316 |
+
"loss": 0.04314669132232666,
|
| 1317 |
+
"step": 9150
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 2.995766851188538,
|
| 1321 |
+
"grad_norm": 0.24384021759033203,
|
| 1322 |
+
"learning_rate": 9.768804949527842e-08,
|
| 1323 |
+
"loss": 0.04970499038696289,
|
| 1324 |
+
"step": 9200
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 3.0,
|
| 1328 |
+
"eval_bertscore_f1": 0.9924511363724068,
|
| 1329 |
+
"eval_bleu": 0.9035076605970417,
|
| 1330 |
+
"eval_loss": 0.058707889169454575,
|
| 1331 |
+
"eval_meteor": 0.9399283468508673,
|
| 1332 |
+
"eval_rouge1": 0.9525840238092467,
|
| 1333 |
+
"eval_rouge2": 0.9200012975801428,
|
| 1334 |
+
"eval_runtime": 58.5972,
|
| 1335 |
+
"eval_samples_per_second": 22.049,
|
| 1336 |
+
"eval_steps_per_second": 2.765,
|
| 1337 |
+
"step": 9213
|
| 1338 |
+
}
|
| 1339 |
+
],
|
| 1340 |
+
"logging_steps": 50,
|
| 1341 |
+
"max_steps": 9213,
|
| 1342 |
+
"num_input_tokens_seen": 0,
|
| 1343 |
+
"num_train_epochs": 3,
|
| 1344 |
+
"save_steps": 500,
|
| 1345 |
+
"stateful_callbacks": {
|
| 1346 |
+
"TrainerControl": {
|
| 1347 |
+
"args": {
|
| 1348 |
+
"should_epoch_stop": false,
|
| 1349 |
+
"should_evaluate": false,
|
| 1350 |
+
"should_log": false,
|
| 1351 |
+
"should_save": true,
|
| 1352 |
+
"should_training_stop": true
|
| 1353 |
+
},
|
| 1354 |
+
"attributes": {}
|
| 1355 |
+
}
|
| 1356 |
+
},
|
| 1357 |
+
"total_flos": 2.24385758724096e+16,
|
| 1358 |
+
"train_batch_size": 8,
|
| 1359 |
+
"trial_name": null,
|
| 1360 |
+
"trial_params": null
|
| 1361 |
+
}
|
checkpoint-9213/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4851cfd31d048ee72e7fd4182be9cde5424ce5abce9d0b7eb67f4b265036230
|
| 3 |
+
size 4920
|
config.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
|
|
|
| 13 |
"eos_token_id": 2,
|
| 14 |
"feed_forward_proj": "relu",
|
| 15 |
"gradient_checkpointing": false,
|
|
@@ -61,8 +62,8 @@
|
|
| 61 |
"prefix": "translate English to Romanian: "
|
| 62 |
}
|
| 63 |
},
|
| 64 |
-
"
|
| 65 |
-
"transformers_version": "
|
| 66 |
-
"use_cache":
|
| 67 |
"vocab_size": 32100
|
| 68 |
}
|
|
|
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
+
"dtype": "float32",
|
| 14 |
"eos_token_id": 2,
|
| 15 |
"feed_forward_proj": "relu",
|
| 16 |
"gradient_checkpointing": false,
|
|
|
|
| 62 |
"prefix": "translate English to Romanian: "
|
| 63 |
}
|
| 64 |
},
|
| 65 |
+
"tie_encoder_decoder": true,
|
| 66 |
+
"transformers_version": "5.0.0rc0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
"vocab_size": 32100
|
| 69 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "
|
| 7 |
}
|
|
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.0.0rc0"
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891558696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:414c84be0b79007c8b483dfa0edc614683a246cb00481cf2e7649a09ab4718e6
|
| 3 |
size 891558696
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -47,906 +61,6 @@
|
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": true,
|
| 49 |
"special": true
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"id": 32000,
|
| 53 |
-
"content": "<extra_id_99>",
|
| 54 |
-
"single_word": false,
|
| 55 |
-
"lstrip": true,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"normalized": true,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"id": 32001,
|
| 62 |
-
"content": "<extra_id_98>",
|
| 63 |
-
"single_word": false,
|
| 64 |
-
"lstrip": true,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"normalized": true,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"id": 32002,
|
| 71 |
-
"content": "<extra_id_97>",
|
| 72 |
-
"single_word": false,
|
| 73 |
-
"lstrip": true,
|
| 74 |
-
"rstrip": false,
|
| 75 |
-
"normalized": true,
|
| 76 |
-
"special": true
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"id": 32003,
|
| 80 |
-
"content": "<extra_id_96>",
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"lstrip": true,
|
| 83 |
-
"rstrip": false,
|
| 84 |
-
"normalized": true,
|
| 85 |
-
"special": true
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"id": 32004,
|
| 89 |
-
"content": "<extra_id_95>",
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"lstrip": true,
|
| 92 |
-
"rstrip": false,
|
| 93 |
-
"normalized": true,
|
| 94 |
-
"special": true
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"id": 32005,
|
| 98 |
-
"content": "<extra_id_94>",
|
| 99 |
-
"single_word": false,
|
| 100 |
-
"lstrip": true,
|
| 101 |
-
"rstrip": false,
|
| 102 |
-
"normalized": true,
|
| 103 |
-
"special": true
|
| 104 |
-
},
|
| 105 |
-
{
|
| 106 |
-
"id": 32006,
|
| 107 |
-
"content": "<extra_id_93>",
|
| 108 |
-
"single_word": false,
|
| 109 |
-
"lstrip": true,
|
| 110 |
-
"rstrip": false,
|
| 111 |
-
"normalized": true,
|
| 112 |
-
"special": true
|
| 113 |
-
},
|
| 114 |
-
{
|
| 115 |
-
"id": 32007,
|
| 116 |
-
"content": "<extra_id_92>",
|
| 117 |
-
"single_word": false,
|
| 118 |
-
"lstrip": true,
|
| 119 |
-
"rstrip": false,
|
| 120 |
-
"normalized": true,
|
| 121 |
-
"special": true
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"id": 32008,
|
| 125 |
-
"content": "<extra_id_91>",
|
| 126 |
-
"single_word": false,
|
| 127 |
-
"lstrip": true,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"normalized": true,
|
| 130 |
-
"special": true
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"id": 32009,
|
| 134 |
-
"content": "<extra_id_90>",
|
| 135 |
-
"single_word": false,
|
| 136 |
-
"lstrip": true,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"normalized": true,
|
| 139 |
-
"special": true
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"id": 32010,
|
| 143 |
-
"content": "<extra_id_89>",
|
| 144 |
-
"single_word": false,
|
| 145 |
-
"lstrip": true,
|
| 146 |
-
"rstrip": false,
|
| 147 |
-
"normalized": true,
|
| 148 |
-
"special": true
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"id": 32011,
|
| 152 |
-
"content": "<extra_id_88>",
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"lstrip": true,
|
| 155 |
-
"rstrip": false,
|
| 156 |
-
"normalized": true,
|
| 157 |
-
"special": true
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"id": 32012,
|
| 161 |
-
"content": "<extra_id_87>",
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"lstrip": true,
|
| 164 |
-
"rstrip": false,
|
| 165 |
-
"normalized": true,
|
| 166 |
-
"special": true
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"id": 32013,
|
| 170 |
-
"content": "<extra_id_86>",
|
| 171 |
-
"single_word": false,
|
| 172 |
-
"lstrip": true,
|
| 173 |
-
"rstrip": false,
|
| 174 |
-
"normalized": true,
|
| 175 |
-
"special": true
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"id": 32014,
|
| 179 |
-
"content": "<extra_id_85>",
|
| 180 |
-
"single_word": false,
|
| 181 |
-
"lstrip": true,
|
| 182 |
-
"rstrip": false,
|
| 183 |
-
"normalized": true,
|
| 184 |
-
"special": true
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"id": 32015,
|
| 188 |
-
"content": "<extra_id_84>",
|
| 189 |
-
"single_word": false,
|
| 190 |
-
"lstrip": true,
|
| 191 |
-
"rstrip": false,
|
| 192 |
-
"normalized": true,
|
| 193 |
-
"special": true
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"id": 32016,
|
| 197 |
-
"content": "<extra_id_83>",
|
| 198 |
-
"single_word": false,
|
| 199 |
-
"lstrip": true,
|
| 200 |
-
"rstrip": false,
|
| 201 |
-
"normalized": true,
|
| 202 |
-
"special": true
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"id": 32017,
|
| 206 |
-
"content": "<extra_id_82>",
|
| 207 |
-
"single_word": false,
|
| 208 |
-
"lstrip": true,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"normalized": true,
|
| 211 |
-
"special": true
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"id": 32018,
|
| 215 |
-
"content": "<extra_id_81>",
|
| 216 |
-
"single_word": false,
|
| 217 |
-
"lstrip": true,
|
| 218 |
-
"rstrip": false,
|
| 219 |
-
"normalized": true,
|
| 220 |
-
"special": true
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"id": 32019,
|
| 224 |
-
"content": "<extra_id_80>",
|
| 225 |
-
"single_word": false,
|
| 226 |
-
"lstrip": true,
|
| 227 |
-
"rstrip": false,
|
| 228 |
-
"normalized": true,
|
| 229 |
-
"special": true
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"id": 32020,
|
| 233 |
-
"content": "<extra_id_79>",
|
| 234 |
-
"single_word": false,
|
| 235 |
-
"lstrip": true,
|
| 236 |
-
"rstrip": false,
|
| 237 |
-
"normalized": true,
|
| 238 |
-
"special": true
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"id": 32021,
|
| 242 |
-
"content": "<extra_id_78>",
|
| 243 |
-
"single_word": false,
|
| 244 |
-
"lstrip": true,
|
| 245 |
-
"rstrip": false,
|
| 246 |
-
"normalized": true,
|
| 247 |
-
"special": true
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"id": 32022,
|
| 251 |
-
"content": "<extra_id_77>",
|
| 252 |
-
"single_word": false,
|
| 253 |
-
"lstrip": true,
|
| 254 |
-
"rstrip": false,
|
| 255 |
-
"normalized": true,
|
| 256 |
-
"special": true
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"id": 32023,
|
| 260 |
-
"content": "<extra_id_76>",
|
| 261 |
-
"single_word": false,
|
| 262 |
-
"lstrip": true,
|
| 263 |
-
"rstrip": false,
|
| 264 |
-
"normalized": true,
|
| 265 |
-
"special": true
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"id": 32024,
|
| 269 |
-
"content": "<extra_id_75>",
|
| 270 |
-
"single_word": false,
|
| 271 |
-
"lstrip": true,
|
| 272 |
-
"rstrip": false,
|
| 273 |
-
"normalized": true,
|
| 274 |
-
"special": true
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"id": 32025,
|
| 278 |
-
"content": "<extra_id_74>",
|
| 279 |
-
"single_word": false,
|
| 280 |
-
"lstrip": true,
|
| 281 |
-
"rstrip": false,
|
| 282 |
-
"normalized": true,
|
| 283 |
-
"special": true
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"id": 32026,
|
| 287 |
-
"content": "<extra_id_73>",
|
| 288 |
-
"single_word": false,
|
| 289 |
-
"lstrip": true,
|
| 290 |
-
"rstrip": false,
|
| 291 |
-
"normalized": true,
|
| 292 |
-
"special": true
|
| 293 |
-
},
|
| 294 |
-
{
|
| 295 |
-
"id": 32027,
|
| 296 |
-
"content": "<extra_id_72>",
|
| 297 |
-
"single_word": false,
|
| 298 |
-
"lstrip": true,
|
| 299 |
-
"rstrip": false,
|
| 300 |
-
"normalized": true,
|
| 301 |
-
"special": true
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"id": 32028,
|
| 305 |
-
"content": "<extra_id_71>",
|
| 306 |
-
"single_word": false,
|
| 307 |
-
"lstrip": true,
|
| 308 |
-
"rstrip": false,
|
| 309 |
-
"normalized": true,
|
| 310 |
-
"special": true
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"id": 32029,
|
| 314 |
-
"content": "<extra_id_70>",
|
| 315 |
-
"single_word": false,
|
| 316 |
-
"lstrip": true,
|
| 317 |
-
"rstrip": false,
|
| 318 |
-
"normalized": true,
|
| 319 |
-
"special": true
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"id": 32030,
|
| 323 |
-
"content": "<extra_id_69>",
|
| 324 |
-
"single_word": false,
|
| 325 |
-
"lstrip": true,
|
| 326 |
-
"rstrip": false,
|
| 327 |
-
"normalized": true,
|
| 328 |
-
"special": true
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"id": 32031,
|
| 332 |
-
"content": "<extra_id_68>",
|
| 333 |
-
"single_word": false,
|
| 334 |
-
"lstrip": true,
|
| 335 |
-
"rstrip": false,
|
| 336 |
-
"normalized": true,
|
| 337 |
-
"special": true
|
| 338 |
-
},
|
| 339 |
-
{
|
| 340 |
-
"id": 32032,
|
| 341 |
-
"content": "<extra_id_67>",
|
| 342 |
-
"single_word": false,
|
| 343 |
-
"lstrip": true,
|
| 344 |
-
"rstrip": false,
|
| 345 |
-
"normalized": true,
|
| 346 |
-
"special": true
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"id": 32033,
|
| 350 |
-
"content": "<extra_id_66>",
|
| 351 |
-
"single_word": false,
|
| 352 |
-
"lstrip": true,
|
| 353 |
-
"rstrip": false,
|
| 354 |
-
"normalized": true,
|
| 355 |
-
"special": true
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"id": 32034,
|
| 359 |
-
"content": "<extra_id_65>",
|
| 360 |
-
"single_word": false,
|
| 361 |
-
"lstrip": true,
|
| 362 |
-
"rstrip": false,
|
| 363 |
-
"normalized": true,
|
| 364 |
-
"special": true
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"id": 32035,
|
| 368 |
-
"content": "<extra_id_64>",
|
| 369 |
-
"single_word": false,
|
| 370 |
-
"lstrip": true,
|
| 371 |
-
"rstrip": false,
|
| 372 |
-
"normalized": true,
|
| 373 |
-
"special": true
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"id": 32036,
|
| 377 |
-
"content": "<extra_id_63>",
|
| 378 |
-
"single_word": false,
|
| 379 |
-
"lstrip": true,
|
| 380 |
-
"rstrip": false,
|
| 381 |
-
"normalized": true,
|
| 382 |
-
"special": true
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"id": 32037,
|
| 386 |
-
"content": "<extra_id_62>",
|
| 387 |
-
"single_word": false,
|
| 388 |
-
"lstrip": true,
|
| 389 |
-
"rstrip": false,
|
| 390 |
-
"normalized": true,
|
| 391 |
-
"special": true
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"id": 32038,
|
| 395 |
-
"content": "<extra_id_61>",
|
| 396 |
-
"single_word": false,
|
| 397 |
-
"lstrip": true,
|
| 398 |
-
"rstrip": false,
|
| 399 |
-
"normalized": true,
|
| 400 |
-
"special": true
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"id": 32039,
|
| 404 |
-
"content": "<extra_id_60>",
|
| 405 |
-
"single_word": false,
|
| 406 |
-
"lstrip": true,
|
| 407 |
-
"rstrip": false,
|
| 408 |
-
"normalized": true,
|
| 409 |
-
"special": true
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"id": 32040,
|
| 413 |
-
"content": "<extra_id_59>",
|
| 414 |
-
"single_word": false,
|
| 415 |
-
"lstrip": true,
|
| 416 |
-
"rstrip": false,
|
| 417 |
-
"normalized": true,
|
| 418 |
-
"special": true
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"id": 32041,
|
| 422 |
-
"content": "<extra_id_58>",
|
| 423 |
-
"single_word": false,
|
| 424 |
-
"lstrip": true,
|
| 425 |
-
"rstrip": false,
|
| 426 |
-
"normalized": true,
|
| 427 |
-
"special": true
|
| 428 |
-
},
|
| 429 |
-
{
|
| 430 |
-
"id": 32042,
|
| 431 |
-
"content": "<extra_id_57>",
|
| 432 |
-
"single_word": false,
|
| 433 |
-
"lstrip": true,
|
| 434 |
-
"rstrip": false,
|
| 435 |
-
"normalized": true,
|
| 436 |
-
"special": true
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"id": 32043,
|
| 440 |
-
"content": "<extra_id_56>",
|
| 441 |
-
"single_word": false,
|
| 442 |
-
"lstrip": true,
|
| 443 |
-
"rstrip": false,
|
| 444 |
-
"normalized": true,
|
| 445 |
-
"special": true
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"id": 32044,
|
| 449 |
-
"content": "<extra_id_55>",
|
| 450 |
-
"single_word": false,
|
| 451 |
-
"lstrip": true,
|
| 452 |
-
"rstrip": false,
|
| 453 |
-
"normalized": true,
|
| 454 |
-
"special": true
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"id": 32045,
|
| 458 |
-
"content": "<extra_id_54>",
|
| 459 |
-
"single_word": false,
|
| 460 |
-
"lstrip": true,
|
| 461 |
-
"rstrip": false,
|
| 462 |
-
"normalized": true,
|
| 463 |
-
"special": true
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"id": 32046,
|
| 467 |
-
"content": "<extra_id_53>",
|
| 468 |
-
"single_word": false,
|
| 469 |
-
"lstrip": true,
|
| 470 |
-
"rstrip": false,
|
| 471 |
-
"normalized": true,
|
| 472 |
-
"special": true
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"id": 32047,
|
| 476 |
-
"content": "<extra_id_52>",
|
| 477 |
-
"single_word": false,
|
| 478 |
-
"lstrip": true,
|
| 479 |
-
"rstrip": false,
|
| 480 |
-
"normalized": true,
|
| 481 |
-
"special": true
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"id": 32048,
|
| 485 |
-
"content": "<extra_id_51>",
|
| 486 |
-
"single_word": false,
|
| 487 |
-
"lstrip": true,
|
| 488 |
-
"rstrip": false,
|
| 489 |
-
"normalized": true,
|
| 490 |
-
"special": true
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"id": 32049,
|
| 494 |
-
"content": "<extra_id_50>",
|
| 495 |
-
"single_word": false,
|
| 496 |
-
"lstrip": true,
|
| 497 |
-
"rstrip": false,
|
| 498 |
-
"normalized": true,
|
| 499 |
-
"special": true
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"id": 32050,
|
| 503 |
-
"content": "<extra_id_49>",
|
| 504 |
-
"single_word": false,
|
| 505 |
-
"lstrip": true,
|
| 506 |
-
"rstrip": false,
|
| 507 |
-
"normalized": true,
|
| 508 |
-
"special": true
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"id": 32051,
|
| 512 |
-
"content": "<extra_id_48>",
|
| 513 |
-
"single_word": false,
|
| 514 |
-
"lstrip": true,
|
| 515 |
-
"rstrip": false,
|
| 516 |
-
"normalized": true,
|
| 517 |
-
"special": true
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"id": 32052,
|
| 521 |
-
"content": "<extra_id_47>",
|
| 522 |
-
"single_word": false,
|
| 523 |
-
"lstrip": true,
|
| 524 |
-
"rstrip": false,
|
| 525 |
-
"normalized": true,
|
| 526 |
-
"special": true
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"id": 32053,
|
| 530 |
-
"content": "<extra_id_46>",
|
| 531 |
-
"single_word": false,
|
| 532 |
-
"lstrip": true,
|
| 533 |
-
"rstrip": false,
|
| 534 |
-
"normalized": true,
|
| 535 |
-
"special": true
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"id": 32054,
|
| 539 |
-
"content": "<extra_id_45>",
|
| 540 |
-
"single_word": false,
|
| 541 |
-
"lstrip": true,
|
| 542 |
-
"rstrip": false,
|
| 543 |
-
"normalized": true,
|
| 544 |
-
"special": true
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"id": 32055,
|
| 548 |
-
"content": "<extra_id_44>",
|
| 549 |
-
"single_word": false,
|
| 550 |
-
"lstrip": true,
|
| 551 |
-
"rstrip": false,
|
| 552 |
-
"normalized": true,
|
| 553 |
-
"special": true
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"id": 32056,
|
| 557 |
-
"content": "<extra_id_43>",
|
| 558 |
-
"single_word": false,
|
| 559 |
-
"lstrip": true,
|
| 560 |
-
"rstrip": false,
|
| 561 |
-
"normalized": true,
|
| 562 |
-
"special": true
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"id": 32057,
|
| 566 |
-
"content": "<extra_id_42>",
|
| 567 |
-
"single_word": false,
|
| 568 |
-
"lstrip": true,
|
| 569 |
-
"rstrip": false,
|
| 570 |
-
"normalized": true,
|
| 571 |
-
"special": true
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"id": 32058,
|
| 575 |
-
"content": "<extra_id_41>",
|
| 576 |
-
"single_word": false,
|
| 577 |
-
"lstrip": true,
|
| 578 |
-
"rstrip": false,
|
| 579 |
-
"normalized": true,
|
| 580 |
-
"special": true
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"id": 32059,
|
| 584 |
-
"content": "<extra_id_40>",
|
| 585 |
-
"single_word": false,
|
| 586 |
-
"lstrip": true,
|
| 587 |
-
"rstrip": false,
|
| 588 |
-
"normalized": true,
|
| 589 |
-
"special": true
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"id": 32060,
|
| 593 |
-
"content": "<extra_id_39>",
|
| 594 |
-
"single_word": false,
|
| 595 |
-
"lstrip": true,
|
| 596 |
-
"rstrip": false,
|
| 597 |
-
"normalized": true,
|
| 598 |
-
"special": true
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"id": 32061,
|
| 602 |
-
"content": "<extra_id_38>",
|
| 603 |
-
"single_word": false,
|
| 604 |
-
"lstrip": true,
|
| 605 |
-
"rstrip": false,
|
| 606 |
-
"normalized": true,
|
| 607 |
-
"special": true
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"id": 32062,
|
| 611 |
-
"content": "<extra_id_37>",
|
| 612 |
-
"single_word": false,
|
| 613 |
-
"lstrip": true,
|
| 614 |
-
"rstrip": false,
|
| 615 |
-
"normalized": true,
|
| 616 |
-
"special": true
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"id": 32063,
|
| 620 |
-
"content": "<extra_id_36>",
|
| 621 |
-
"single_word": false,
|
| 622 |
-
"lstrip": true,
|
| 623 |
-
"rstrip": false,
|
| 624 |
-
"normalized": true,
|
| 625 |
-
"special": true
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"id": 32064,
|
| 629 |
-
"content": "<extra_id_35>",
|
| 630 |
-
"single_word": false,
|
| 631 |
-
"lstrip": true,
|
| 632 |
-
"rstrip": false,
|
| 633 |
-
"normalized": true,
|
| 634 |
-
"special": true
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"id": 32065,
|
| 638 |
-
"content": "<extra_id_34>",
|
| 639 |
-
"single_word": false,
|
| 640 |
-
"lstrip": true,
|
| 641 |
-
"rstrip": false,
|
| 642 |
-
"normalized": true,
|
| 643 |
-
"special": true
|
| 644 |
-
},
|
| 645 |
-
{
|
| 646 |
-
"id": 32066,
|
| 647 |
-
"content": "<extra_id_33>",
|
| 648 |
-
"single_word": false,
|
| 649 |
-
"lstrip": true,
|
| 650 |
-
"rstrip": false,
|
| 651 |
-
"normalized": true,
|
| 652 |
-
"special": true
|
| 653 |
-
},
|
| 654 |
-
{
|
| 655 |
-
"id": 32067,
|
| 656 |
-
"content": "<extra_id_32>",
|
| 657 |
-
"single_word": false,
|
| 658 |
-
"lstrip": true,
|
| 659 |
-
"rstrip": false,
|
| 660 |
-
"normalized": true,
|
| 661 |
-
"special": true
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"id": 32068,
|
| 665 |
-
"content": "<extra_id_31>",
|
| 666 |
-
"single_word": false,
|
| 667 |
-
"lstrip": true,
|
| 668 |
-
"rstrip": false,
|
| 669 |
-
"normalized": true,
|
| 670 |
-
"special": true
|
| 671 |
-
},
|
| 672 |
-
{
|
| 673 |
-
"id": 32069,
|
| 674 |
-
"content": "<extra_id_30>",
|
| 675 |
-
"single_word": false,
|
| 676 |
-
"lstrip": true,
|
| 677 |
-
"rstrip": false,
|
| 678 |
-
"normalized": true,
|
| 679 |
-
"special": true
|
| 680 |
-
},
|
| 681 |
-
{
|
| 682 |
-
"id": 32070,
|
| 683 |
-
"content": "<extra_id_29>",
|
| 684 |
-
"single_word": false,
|
| 685 |
-
"lstrip": true,
|
| 686 |
-
"rstrip": false,
|
| 687 |
-
"normalized": true,
|
| 688 |
-
"special": true
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"id": 32071,
|
| 692 |
-
"content": "<extra_id_28>",
|
| 693 |
-
"single_word": false,
|
| 694 |
-
"lstrip": true,
|
| 695 |
-
"rstrip": false,
|
| 696 |
-
"normalized": true,
|
| 697 |
-
"special": true
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"id": 32072,
|
| 701 |
-
"content": "<extra_id_27>",
|
| 702 |
-
"single_word": false,
|
| 703 |
-
"lstrip": true,
|
| 704 |
-
"rstrip": false,
|
| 705 |
-
"normalized": true,
|
| 706 |
-
"special": true
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"id": 32073,
|
| 710 |
-
"content": "<extra_id_26>",
|
| 711 |
-
"single_word": false,
|
| 712 |
-
"lstrip": true,
|
| 713 |
-
"rstrip": false,
|
| 714 |
-
"normalized": true,
|
| 715 |
-
"special": true
|
| 716 |
-
},
|
| 717 |
-
{
|
| 718 |
-
"id": 32074,
|
| 719 |
-
"content": "<extra_id_25>",
|
| 720 |
-
"single_word": false,
|
| 721 |
-
"lstrip": true,
|
| 722 |
-
"rstrip": false,
|
| 723 |
-
"normalized": true,
|
| 724 |
-
"special": true
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"id": 32075,
|
| 728 |
-
"content": "<extra_id_24>",
|
| 729 |
-
"single_word": false,
|
| 730 |
-
"lstrip": true,
|
| 731 |
-
"rstrip": false,
|
| 732 |
-
"normalized": true,
|
| 733 |
-
"special": true
|
| 734 |
-
},
|
| 735 |
-
{
|
| 736 |
-
"id": 32076,
|
| 737 |
-
"content": "<extra_id_23>",
|
| 738 |
-
"single_word": false,
|
| 739 |
-
"lstrip": true,
|
| 740 |
-
"rstrip": false,
|
| 741 |
-
"normalized": true,
|
| 742 |
-
"special": true
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"id": 32077,
|
| 746 |
-
"content": "<extra_id_22>",
|
| 747 |
-
"single_word": false,
|
| 748 |
-
"lstrip": true,
|
| 749 |
-
"rstrip": false,
|
| 750 |
-
"normalized": true,
|
| 751 |
-
"special": true
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"id": 32078,
|
| 755 |
-
"content": "<extra_id_21>",
|
| 756 |
-
"single_word": false,
|
| 757 |
-
"lstrip": true,
|
| 758 |
-
"rstrip": false,
|
| 759 |
-
"normalized": true,
|
| 760 |
-
"special": true
|
| 761 |
-
},
|
| 762 |
-
{
|
| 763 |
-
"id": 32079,
|
| 764 |
-
"content": "<extra_id_20>",
|
| 765 |
-
"single_word": false,
|
| 766 |
-
"lstrip": true,
|
| 767 |
-
"rstrip": false,
|
| 768 |
-
"normalized": true,
|
| 769 |
-
"special": true
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"id": 32080,
|
| 773 |
-
"content": "<extra_id_19>",
|
| 774 |
-
"single_word": false,
|
| 775 |
-
"lstrip": true,
|
| 776 |
-
"rstrip": false,
|
| 777 |
-
"normalized": true,
|
| 778 |
-
"special": true
|
| 779 |
-
},
|
| 780 |
-
{
|
| 781 |
-
"id": 32081,
|
| 782 |
-
"content": "<extra_id_18>",
|
| 783 |
-
"single_word": false,
|
| 784 |
-
"lstrip": true,
|
| 785 |
-
"rstrip": false,
|
| 786 |
-
"normalized": true,
|
| 787 |
-
"special": true
|
| 788 |
-
},
|
| 789 |
-
{
|
| 790 |
-
"id": 32082,
|
| 791 |
-
"content": "<extra_id_17>",
|
| 792 |
-
"single_word": false,
|
| 793 |
-
"lstrip": true,
|
| 794 |
-
"rstrip": false,
|
| 795 |
-
"normalized": true,
|
| 796 |
-
"special": true
|
| 797 |
-
},
|
| 798 |
-
{
|
| 799 |
-
"id": 32083,
|
| 800 |
-
"content": "<extra_id_16>",
|
| 801 |
-
"single_word": false,
|
| 802 |
-
"lstrip": true,
|
| 803 |
-
"rstrip": false,
|
| 804 |
-
"normalized": true,
|
| 805 |
-
"special": true
|
| 806 |
-
},
|
| 807 |
-
{
|
| 808 |
-
"id": 32084,
|
| 809 |
-
"content": "<extra_id_15>",
|
| 810 |
-
"single_word": false,
|
| 811 |
-
"lstrip": true,
|
| 812 |
-
"rstrip": false,
|
| 813 |
-
"normalized": true,
|
| 814 |
-
"special": true
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"id": 32085,
|
| 818 |
-
"content": "<extra_id_14>",
|
| 819 |
-
"single_word": false,
|
| 820 |
-
"lstrip": true,
|
| 821 |
-
"rstrip": false,
|
| 822 |
-
"normalized": true,
|
| 823 |
-
"special": true
|
| 824 |
-
},
|
| 825 |
-
{
|
| 826 |
-
"id": 32086,
|
| 827 |
-
"content": "<extra_id_13>",
|
| 828 |
-
"single_word": false,
|
| 829 |
-
"lstrip": true,
|
| 830 |
-
"rstrip": false,
|
| 831 |
-
"normalized": true,
|
| 832 |
-
"special": true
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"id": 32087,
|
| 836 |
-
"content": "<extra_id_12>",
|
| 837 |
-
"single_word": false,
|
| 838 |
-
"lstrip": true,
|
| 839 |
-
"rstrip": false,
|
| 840 |
-
"normalized": true,
|
| 841 |
-
"special": true
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"id": 32088,
|
| 845 |
-
"content": "<extra_id_11>",
|
| 846 |
-
"single_word": false,
|
| 847 |
-
"lstrip": true,
|
| 848 |
-
"rstrip": false,
|
| 849 |
-
"normalized": true,
|
| 850 |
-
"special": true
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"id": 32089,
|
| 854 |
-
"content": "<extra_id_10>",
|
| 855 |
-
"single_word": false,
|
| 856 |
-
"lstrip": true,
|
| 857 |
-
"rstrip": false,
|
| 858 |
-
"normalized": true,
|
| 859 |
-
"special": true
|
| 860 |
-
},
|
| 861 |
-
{
|
| 862 |
-
"id": 32090,
|
| 863 |
-
"content": "<extra_id_9>",
|
| 864 |
-
"single_word": false,
|
| 865 |
-
"lstrip": true,
|
| 866 |
-
"rstrip": false,
|
| 867 |
-
"normalized": true,
|
| 868 |
-
"special": true
|
| 869 |
-
},
|
| 870 |
-
{
|
| 871 |
-
"id": 32091,
|
| 872 |
-
"content": "<extra_id_8>",
|
| 873 |
-
"single_word": false,
|
| 874 |
-
"lstrip": true,
|
| 875 |
-
"rstrip": false,
|
| 876 |
-
"normalized": true,
|
| 877 |
-
"special": true
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"id": 32092,
|
| 881 |
-
"content": "<extra_id_7>",
|
| 882 |
-
"single_word": false,
|
| 883 |
-
"lstrip": true,
|
| 884 |
-
"rstrip": false,
|
| 885 |
-
"normalized": true,
|
| 886 |
-
"special": true
|
| 887 |
-
},
|
| 888 |
-
{
|
| 889 |
-
"id": 32093,
|
| 890 |
-
"content": "<extra_id_6>",
|
| 891 |
-
"single_word": false,
|
| 892 |
-
"lstrip": true,
|
| 893 |
-
"rstrip": false,
|
| 894 |
-
"normalized": true,
|
| 895 |
-
"special": true
|
| 896 |
-
},
|
| 897 |
-
{
|
| 898 |
-
"id": 32094,
|
| 899 |
-
"content": "<extra_id_5>",
|
| 900 |
-
"single_word": false,
|
| 901 |
-
"lstrip": true,
|
| 902 |
-
"rstrip": false,
|
| 903 |
-
"normalized": true,
|
| 904 |
-
"special": true
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"id": 32095,
|
| 908 |
-
"content": "<extra_id_4>",
|
| 909 |
-
"single_word": false,
|
| 910 |
-
"lstrip": true,
|
| 911 |
-
"rstrip": false,
|
| 912 |
-
"normalized": true,
|
| 913 |
-
"special": true
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"id": 32096,
|
| 917 |
-
"content": "<extra_id_3>",
|
| 918 |
-
"single_word": false,
|
| 919 |
-
"lstrip": true,
|
| 920 |
-
"rstrip": false,
|
| 921 |
-
"normalized": true,
|
| 922 |
-
"special": true
|
| 923 |
-
},
|
| 924 |
-
{
|
| 925 |
-
"id": 32097,
|
| 926 |
-
"content": "<extra_id_2>",
|
| 927 |
-
"single_word": false,
|
| 928 |
-
"lstrip": true,
|
| 929 |
-
"rstrip": false,
|
| 930 |
-
"normalized": true,
|
| 931 |
-
"special": true
|
| 932 |
-
},
|
| 933 |
-
{
|
| 934 |
-
"id": 32098,
|
| 935 |
-
"content": "<extra_id_1>",
|
| 936 |
-
"single_word": false,
|
| 937 |
-
"lstrip": true,
|
| 938 |
-
"rstrip": false,
|
| 939 |
-
"normalized": true,
|
| 940 |
-
"special": true
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"id": 32099,
|
| 944 |
-
"content": "<extra_id_0>",
|
| 945 |
-
"single_word": false,
|
| 946 |
-
"lstrip": true,
|
| 947 |
-
"rstrip": false,
|
| 948 |
-
"normalized": true,
|
| 949 |
-
"special": true
|
| 950 |
}
|
| 951 |
],
|
| 952 |
"normalizer": null,
|
|
@@ -36799,10 +35913,6 @@
|
|
| 36799 |
"pr",
|
| 36800 |
"int"
|
| 36801 |
],
|
| 36802 |
-
[
|
| 36803 |
-
"#",
|
| 36804 |
-
"#"
|
| 36805 |
-
],
|
| 36806 |
[
|
| 36807 |
"W",
|
| 36808 |
"ith"
|
|
@@ -39923,10 +39033,6 @@
|
|
| 39923 |
"b",
|
| 39924 |
"ase"
|
| 39925 |
],
|
| 39926 |
-
[
|
| 39927 |
-
"##",
|
| 39928 |
-
"##"
|
| 39929 |
-
],
|
| 39930 |
[
|
| 39931 |
"R",
|
| 39932 |
"el"
|
|
@@ -44955,10 +44061,6 @@
|
|
| 44955 |
"Ġre",
|
| 44956 |
"trie"
|
| 44957 |
],
|
| 44958 |
-
[
|
| 44959 |
-
"####",
|
| 44960 |
-
"####"
|
| 44961 |
-
],
|
| 44962 |
[
|
| 44963 |
"Ġmult",
|
| 44964 |
"iple"
|
|
@@ -46611,10 +45713,6 @@
|
|
| 46611 |
"At",
|
| 46612 |
"om"
|
| 46613 |
],
|
| 46614 |
-
[
|
| 46615 |
-
"#",
|
| 46616 |
-
"{"
|
| 46617 |
-
],
|
| 46618 |
[
|
| 46619 |
"Ġro",
|
| 46620 |
"und"
|
|
@@ -54107,10 +53205,6 @@
|
|
| 54107 |
"Ġex",
|
| 54108 |
"plicit"
|
| 54109 |
],
|
| 54110 |
-
[
|
| 54111 |
-
"########",
|
| 54112 |
-
"########"
|
| 54113 |
-
],
|
| 54114 |
[
|
| 54115 |
"Service",
|
| 54116 |
"Response"
|
|
@@ -72195,10 +71289,6 @@
|
|
| 72195 |
"el",
|
| 72196 |
"em"
|
| 72197 |
],
|
| 72198 |
-
[
|
| 72199 |
-
"#",
|
| 72200 |
-
"'"
|
| 72201 |
-
],
|
| 72202 |
[
|
| 72203 |
"Ġcon",
|
| 72204 |
"versation"
|
|
@@ -72603,10 +71693,6 @@
|
|
| 72603 |
"ĠPre",
|
| 72604 |
"fix"
|
| 72605 |
],
|
| 72606 |
-
[
|
| 72607 |
-
"################",
|
| 72608 |
-
"################"
|
| 72609 |
-
],
|
| 72610 |
[
|
| 72611 |
"s",
|
| 72612 |
"ources"
|
|
@@ -84647,10 +83733,6 @@
|
|
| 84647 |
"Ġh",
|
| 84648 |
"el"
|
| 84649 |
],
|
| 84650 |
-
[
|
| 84651 |
-
"##",
|
| 84652 |
-
"#"
|
| 84653 |
-
],
|
| 84654 |
[
|
| 84655 |
"And",
|
| 84656 |
"Set"
|
|
@@ -100575,10 +99657,6 @@
|
|
| 100575 |
"Ġrule",
|
| 100576 |
"ValidID"
|
| 100577 |
],
|
| 100578 |
-
[
|
| 100579 |
-
"#",
|
| 100580 |
-
"\""
|
| 100581 |
-
],
|
| 100582 |
[
|
| 100583 |
"^",
|
| 100584 |
"\\"
|
|
@@ -116607,10 +115685,6 @@
|
|
| 116607 |
"ĠUn",
|
| 116608 |
"der"
|
| 116609 |
],
|
| 116610 |
-
[
|
| 116611 |
-
"#{",
|
| 116612 |
-
"@"
|
| 116613 |
-
],
|
| 116614 |
[
|
| 116615 |
"ĠAct",
|
| 116616 |
"or"
|
|
@@ -137991,10 +137065,6 @@
|
|
| 137991 |
"Queue",
|
| 137992 |
"Entry"
|
| 137993 |
],
|
| 137994 |
-
[
|
| 137995 |
-
"########",
|
| 137996 |
-
"####"
|
| 137997 |
-
],
|
| 137998 |
[
|
| 137999 |
"alan",
|
| 138000 |
"ces"
|
|
@@ -154031,10 +153101,6 @@
|
|
| 154031 |
"SETT",
|
| 154032 |
"ABLE"
|
| 154033 |
],
|
| 154034 |
-
[
|
| 154035 |
-
"#",
|
| 154036 |
-
"$"
|
| 154037 |
-
],
|
| 154038 |
[
|
| 154039 |
"C",
|
| 154040 |
"ores"
|
|
@@ -154435,10 +153501,6 @@
|
|
| 154435 |
"ENDI",
|
| 154436 |
"AN"
|
| 154437 |
],
|
| 154438 |
-
[
|
| 154439 |
-
"#",
|
| 154440 |
-
"__"
|
| 154441 |
-
],
|
| 154442 |
[
|
| 154443 |
">",
|
| 154444 |
"`"
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 256,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 256
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<pad>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 61 |
"rstrip": false,
|
| 62 |
"normalized": true,
|
| 63 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
}
|
| 65 |
],
|
| 66 |
"normalizer": null,
|
|
|
|
| 35913 |
"pr",
|
| 35914 |
"int"
|
| 35915 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35916 |
[
|
| 35917 |
"W",
|
| 35918 |
"ith"
|
|
|
|
| 39033 |
"b",
|
| 39034 |
"ase"
|
| 39035 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39036 |
[
|
| 39037 |
"R",
|
| 39038 |
"el"
|
|
|
|
| 44061 |
"Ġre",
|
| 44062 |
"trie"
|
| 44063 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44064 |
[
|
| 44065 |
"Ġmult",
|
| 44066 |
"iple"
|
|
|
|
| 45713 |
"At",
|
| 45714 |
"om"
|
| 45715 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45716 |
[
|
| 45717 |
"Ġro",
|
| 45718 |
"und"
|
|
|
|
| 53205 |
"Ġex",
|
| 53206 |
"plicit"
|
| 53207 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53208 |
[
|
| 53209 |
"Service",
|
| 53210 |
"Response"
|
|
|
|
| 71289 |
"el",
|
| 71290 |
"em"
|
| 71291 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71292 |
[
|
| 71293 |
"Ġcon",
|
| 71294 |
"versation"
|
|
|
|
| 71693 |
"ĠPre",
|
| 71694 |
"fix"
|
| 71695 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71696 |
[
|
| 71697 |
"s",
|
| 71698 |
"ources"
|
|
|
|
| 83733 |
"Ġh",
|
| 83734 |
"el"
|
| 83735 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83736 |
[
|
| 83737 |
"And",
|
| 83738 |
"Set"
|
|
|
|
| 99657 |
"Ġrule",
|
| 99658 |
"ValidID"
|
| 99659 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99660 |
[
|
| 99661 |
"^",
|
| 99662 |
"\\"
|
|
|
|
| 115685 |
"ĠUn",
|
| 115686 |
"der"
|
| 115687 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115688 |
[
|
| 115689 |
"ĠAct",
|
| 115690 |
"or"
|
|
|
|
| 137065 |
"Queue",
|
| 137066 |
"Entry"
|
| 137067 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137068 |
[
|
| 137069 |
"alan",
|
| 137070 |
"ces"
|
|
|
|
| 153101 |
"SETT",
|
| 153102 |
"ABLE"
|
| 153103 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153104 |
[
|
| 153105 |
"C",
|
| 153106 |
"ores"
|
|
|
|
| 153501 |
"ENDI",
|
| 153502 |
"AN"
|
| 153503 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153504 |
[
|
| 153505 |
">",
|
| 153506 |
"`"
|
tokenizer_config.json
CHANGED
|
@@ -1,955 +1,714 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
"content": "<pad>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<s>",
|
| 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 |
-
"4": {
|
| 37 |
-
"content": "<mask>",
|
| 38 |
-
"lstrip": true,
|
| 39 |
-
"normalized": true,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"32000": {
|
| 45 |
"content": "<extra_id_99>",
|
| 46 |
"lstrip": true,
|
| 47 |
"normalized": true,
|
| 48 |
"rstrip": false,
|
| 49 |
-
"single_word": false
|
| 50 |
-
"special": true
|
| 51 |
},
|
| 52 |
-
|
| 53 |
"content": "<extra_id_98>",
|
| 54 |
"lstrip": true,
|
| 55 |
"normalized": true,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"single_word": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
-
|
| 61 |
"content": "<extra_id_97>",
|
| 62 |
"lstrip": true,
|
| 63 |
"normalized": true,
|
| 64 |
"rstrip": false,
|
| 65 |
-
"single_word": false
|
| 66 |
-
"special": true
|
| 67 |
},
|
| 68 |
-
|
| 69 |
"content": "<extra_id_96>",
|
| 70 |
"lstrip": true,
|
| 71 |
"normalized": true,
|
| 72 |
"rstrip": false,
|
| 73 |
-
"single_word": false
|
| 74 |
-
"special": true
|
| 75 |
},
|
| 76 |
-
|
| 77 |
"content": "<extra_id_95>",
|
| 78 |
"lstrip": true,
|
| 79 |
"normalized": true,
|
| 80 |
"rstrip": false,
|
| 81 |
-
"single_word": false
|
| 82 |
-
"special": true
|
| 83 |
},
|
| 84 |
-
|
| 85 |
"content": "<extra_id_94>",
|
| 86 |
"lstrip": true,
|
| 87 |
"normalized": true,
|
| 88 |
"rstrip": false,
|
| 89 |
-
"single_word": false
|
| 90 |
-
"special": true
|
| 91 |
},
|
| 92 |
-
|
| 93 |
"content": "<extra_id_93>",
|
| 94 |
"lstrip": true,
|
| 95 |
"normalized": true,
|
| 96 |
"rstrip": false,
|
| 97 |
-
"single_word": false
|
| 98 |
-
"special": true
|
| 99 |
},
|
| 100 |
-
|
| 101 |
"content": "<extra_id_92>",
|
| 102 |
"lstrip": true,
|
| 103 |
"normalized": true,
|
| 104 |
"rstrip": false,
|
| 105 |
-
"single_word": false
|
| 106 |
-
"special": true
|
| 107 |
},
|
| 108 |
-
|
| 109 |
"content": "<extra_id_91>",
|
| 110 |
"lstrip": true,
|
| 111 |
"normalized": true,
|
| 112 |
"rstrip": false,
|
| 113 |
-
"single_word": false
|
| 114 |
-
"special": true
|
| 115 |
},
|
| 116 |
-
|
| 117 |
"content": "<extra_id_90>",
|
| 118 |
"lstrip": true,
|
| 119 |
"normalized": true,
|
| 120 |
"rstrip": false,
|
| 121 |
-
"single_word": false
|
| 122 |
-
"special": true
|
| 123 |
},
|
| 124 |
-
|
| 125 |
"content": "<extra_id_89>",
|
| 126 |
"lstrip": true,
|
| 127 |
"normalized": true,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"single_word": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
-
|
| 133 |
"content": "<extra_id_88>",
|
| 134 |
"lstrip": true,
|
| 135 |
"normalized": true,
|
| 136 |
"rstrip": false,
|
| 137 |
-
"single_word": false
|
| 138 |
-
"special": true
|
| 139 |
},
|
| 140 |
-
|
| 141 |
"content": "<extra_id_87>",
|
| 142 |
"lstrip": true,
|
| 143 |
"normalized": true,
|
| 144 |
"rstrip": false,
|
| 145 |
-
"single_word": false
|
| 146 |
-
"special": true
|
| 147 |
},
|
| 148 |
-
|
| 149 |
"content": "<extra_id_86>",
|
| 150 |
"lstrip": true,
|
| 151 |
"normalized": true,
|
| 152 |
"rstrip": false,
|
| 153 |
-
"single_word": false
|
| 154 |
-
"special": true
|
| 155 |
},
|
| 156 |
-
|
| 157 |
"content": "<extra_id_85>",
|
| 158 |
"lstrip": true,
|
| 159 |
"normalized": true,
|
| 160 |
"rstrip": false,
|
| 161 |
-
"single_word": false
|
| 162 |
-
"special": true
|
| 163 |
},
|
| 164 |
-
|
| 165 |
"content": "<extra_id_84>",
|
| 166 |
"lstrip": true,
|
| 167 |
"normalized": true,
|
| 168 |
"rstrip": false,
|
| 169 |
-
"single_word": false
|
| 170 |
-
"special": true
|
| 171 |
},
|
| 172 |
-
|
| 173 |
"content": "<extra_id_83>",
|
| 174 |
"lstrip": true,
|
| 175 |
"normalized": true,
|
| 176 |
"rstrip": false,
|
| 177 |
-
"single_word": false
|
| 178 |
-
"special": true
|
| 179 |
},
|
| 180 |
-
|
| 181 |
"content": "<extra_id_82>",
|
| 182 |
"lstrip": true,
|
| 183 |
"normalized": true,
|
| 184 |
"rstrip": false,
|
| 185 |
-
"single_word": false
|
| 186 |
-
"special": true
|
| 187 |
},
|
| 188 |
-
|
| 189 |
"content": "<extra_id_81>",
|
| 190 |
"lstrip": true,
|
| 191 |
"normalized": true,
|
| 192 |
"rstrip": false,
|
| 193 |
-
"single_word": false
|
| 194 |
-
"special": true
|
| 195 |
},
|
| 196 |
-
|
| 197 |
"content": "<extra_id_80>",
|
| 198 |
"lstrip": true,
|
| 199 |
"normalized": true,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"single_word": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
-
|
| 205 |
"content": "<extra_id_79>",
|
| 206 |
"lstrip": true,
|
| 207 |
"normalized": true,
|
| 208 |
"rstrip": false,
|
| 209 |
-
"single_word": false
|
| 210 |
-
"special": true
|
| 211 |
},
|
| 212 |
-
|
| 213 |
"content": "<extra_id_78>",
|
| 214 |
"lstrip": true,
|
| 215 |
"normalized": true,
|
| 216 |
"rstrip": false,
|
| 217 |
-
"single_word": false
|
| 218 |
-
"special": true
|
| 219 |
},
|
| 220 |
-
|
| 221 |
"content": "<extra_id_77>",
|
| 222 |
"lstrip": true,
|
| 223 |
"normalized": true,
|
| 224 |
"rstrip": false,
|
| 225 |
-
"single_word": false
|
| 226 |
-
"special": true
|
| 227 |
},
|
| 228 |
-
|
| 229 |
"content": "<extra_id_76>",
|
| 230 |
"lstrip": true,
|
| 231 |
"normalized": true,
|
| 232 |
"rstrip": false,
|
| 233 |
-
"single_word": false
|
| 234 |
-
"special": true
|
| 235 |
},
|
| 236 |
-
|
| 237 |
"content": "<extra_id_75>",
|
| 238 |
"lstrip": true,
|
| 239 |
"normalized": true,
|
| 240 |
"rstrip": false,
|
| 241 |
-
"single_word": false
|
| 242 |
-
"special": true
|
| 243 |
},
|
| 244 |
-
|
| 245 |
"content": "<extra_id_74>",
|
| 246 |
"lstrip": true,
|
| 247 |
"normalized": true,
|
| 248 |
"rstrip": false,
|
| 249 |
-
"single_word": false
|
| 250 |
-
"special": true
|
| 251 |
},
|
| 252 |
-
|
| 253 |
"content": "<extra_id_73>",
|
| 254 |
"lstrip": true,
|
| 255 |
"normalized": true,
|
| 256 |
"rstrip": false,
|
| 257 |
-
"single_word": false
|
| 258 |
-
"special": true
|
| 259 |
},
|
| 260 |
-
|
| 261 |
"content": "<extra_id_72>",
|
| 262 |
"lstrip": true,
|
| 263 |
"normalized": true,
|
| 264 |
"rstrip": false,
|
| 265 |
-
"single_word": false
|
| 266 |
-
"special": true
|
| 267 |
},
|
| 268 |
-
|
| 269 |
"content": "<extra_id_71>",
|
| 270 |
"lstrip": true,
|
| 271 |
"normalized": true,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"single_word": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
-
|
| 277 |
"content": "<extra_id_70>",
|
| 278 |
"lstrip": true,
|
| 279 |
"normalized": true,
|
| 280 |
"rstrip": false,
|
| 281 |
-
"single_word": false
|
| 282 |
-
"special": true
|
| 283 |
},
|
| 284 |
-
|
| 285 |
"content": "<extra_id_69>",
|
| 286 |
"lstrip": true,
|
| 287 |
"normalized": true,
|
| 288 |
"rstrip": false,
|
| 289 |
-
"single_word": false
|
| 290 |
-
"special": true
|
| 291 |
},
|
| 292 |
-
|
| 293 |
"content": "<extra_id_68>",
|
| 294 |
"lstrip": true,
|
| 295 |
"normalized": true,
|
| 296 |
"rstrip": false,
|
| 297 |
-
"single_word": false
|
| 298 |
-
"special": true
|
| 299 |
},
|
| 300 |
-
|
| 301 |
"content": "<extra_id_67>",
|
| 302 |
"lstrip": true,
|
| 303 |
"normalized": true,
|
| 304 |
"rstrip": false,
|
| 305 |
-
"single_word": false
|
| 306 |
-
"special": true
|
| 307 |
},
|
| 308 |
-
|
| 309 |
"content": "<extra_id_66>",
|
| 310 |
"lstrip": true,
|
| 311 |
"normalized": true,
|
| 312 |
"rstrip": false,
|
| 313 |
-
"single_word": false
|
| 314 |
-
"special": true
|
| 315 |
},
|
| 316 |
-
|
| 317 |
"content": "<extra_id_65>",
|
| 318 |
"lstrip": true,
|
| 319 |
"normalized": true,
|
| 320 |
"rstrip": false,
|
| 321 |
-
"single_word": false
|
| 322 |
-
"special": true
|
| 323 |
},
|
| 324 |
-
|
| 325 |
"content": "<extra_id_64>",
|
| 326 |
"lstrip": true,
|
| 327 |
"normalized": true,
|
| 328 |
"rstrip": false,
|
| 329 |
-
"single_word": false
|
| 330 |
-
"special": true
|
| 331 |
},
|
| 332 |
-
|
| 333 |
"content": "<extra_id_63>",
|
| 334 |
"lstrip": true,
|
| 335 |
"normalized": true,
|
| 336 |
"rstrip": false,
|
| 337 |
-
"single_word": false
|
| 338 |
-
"special": true
|
| 339 |
},
|
| 340 |
-
|
| 341 |
"content": "<extra_id_62>",
|
| 342 |
"lstrip": true,
|
| 343 |
"normalized": true,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"single_word": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
-
|
| 349 |
"content": "<extra_id_61>",
|
| 350 |
"lstrip": true,
|
| 351 |
"normalized": true,
|
| 352 |
"rstrip": false,
|
| 353 |
-
"single_word": false
|
| 354 |
-
"special": true
|
| 355 |
},
|
| 356 |
-
|
| 357 |
"content": "<extra_id_60>",
|
| 358 |
"lstrip": true,
|
| 359 |
"normalized": true,
|
| 360 |
"rstrip": false,
|
| 361 |
-
"single_word": false
|
| 362 |
-
"special": true
|
| 363 |
},
|
| 364 |
-
|
| 365 |
"content": "<extra_id_59>",
|
| 366 |
"lstrip": true,
|
| 367 |
"normalized": true,
|
| 368 |
"rstrip": false,
|
| 369 |
-
"single_word": false
|
| 370 |
-
"special": true
|
| 371 |
},
|
| 372 |
-
|
| 373 |
"content": "<extra_id_58>",
|
| 374 |
"lstrip": true,
|
| 375 |
"normalized": true,
|
| 376 |
"rstrip": false,
|
| 377 |
-
"single_word": false
|
| 378 |
-
"special": true
|
| 379 |
},
|
| 380 |
-
|
| 381 |
"content": "<extra_id_57>",
|
| 382 |
"lstrip": true,
|
| 383 |
"normalized": true,
|
| 384 |
"rstrip": false,
|
| 385 |
-
"single_word": false
|
| 386 |
-
"special": true
|
| 387 |
},
|
| 388 |
-
|
| 389 |
"content": "<extra_id_56>",
|
| 390 |
"lstrip": true,
|
| 391 |
"normalized": true,
|
| 392 |
"rstrip": false,
|
| 393 |
-
"single_word": false
|
| 394 |
-
"special": true
|
| 395 |
},
|
| 396 |
-
|
| 397 |
"content": "<extra_id_55>",
|
| 398 |
"lstrip": true,
|
| 399 |
"normalized": true,
|
| 400 |
"rstrip": false,
|
| 401 |
-
"single_word": false
|
| 402 |
-
"special": true
|
| 403 |
},
|
| 404 |
-
|
| 405 |
"content": "<extra_id_54>",
|
| 406 |
"lstrip": true,
|
| 407 |
"normalized": true,
|
| 408 |
"rstrip": false,
|
| 409 |
-
"single_word": false
|
| 410 |
-
"special": true
|
| 411 |
},
|
| 412 |
-
|
| 413 |
"content": "<extra_id_53>",
|
| 414 |
"lstrip": true,
|
| 415 |
"normalized": true,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"single_word": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
-
|
| 421 |
"content": "<extra_id_52>",
|
| 422 |
"lstrip": true,
|
| 423 |
"normalized": true,
|
| 424 |
"rstrip": false,
|
| 425 |
-
"single_word": false
|
| 426 |
-
"special": true
|
| 427 |
},
|
| 428 |
-
|
| 429 |
"content": "<extra_id_51>",
|
| 430 |
"lstrip": true,
|
| 431 |
"normalized": true,
|
| 432 |
"rstrip": false,
|
| 433 |
-
"single_word": false
|
| 434 |
-
"special": true
|
| 435 |
},
|
| 436 |
-
|
| 437 |
"content": "<extra_id_50>",
|
| 438 |
"lstrip": true,
|
| 439 |
"normalized": true,
|
| 440 |
"rstrip": false,
|
| 441 |
-
"single_word": false
|
| 442 |
-
"special": true
|
| 443 |
},
|
| 444 |
-
|
| 445 |
"content": "<extra_id_49>",
|
| 446 |
"lstrip": true,
|
| 447 |
"normalized": true,
|
| 448 |
"rstrip": false,
|
| 449 |
-
"single_word": false
|
| 450 |
-
"special": true
|
| 451 |
},
|
| 452 |
-
|
| 453 |
"content": "<extra_id_48>",
|
| 454 |
"lstrip": true,
|
| 455 |
"normalized": true,
|
| 456 |
"rstrip": false,
|
| 457 |
-
"single_word": false
|
| 458 |
-
"special": true
|
| 459 |
},
|
| 460 |
-
|
| 461 |
"content": "<extra_id_47>",
|
| 462 |
"lstrip": true,
|
| 463 |
"normalized": true,
|
| 464 |
"rstrip": false,
|
| 465 |
-
"single_word": false
|
| 466 |
-
"special": true
|
| 467 |
},
|
| 468 |
-
|
| 469 |
"content": "<extra_id_46>",
|
| 470 |
"lstrip": true,
|
| 471 |
"normalized": true,
|
| 472 |
"rstrip": false,
|
| 473 |
-
"single_word": false
|
| 474 |
-
"special": true
|
| 475 |
},
|
| 476 |
-
|
| 477 |
"content": "<extra_id_45>",
|
| 478 |
"lstrip": true,
|
| 479 |
"normalized": true,
|
| 480 |
"rstrip": false,
|
| 481 |
-
"single_word": false
|
| 482 |
-
"special": true
|
| 483 |
},
|
| 484 |
-
|
| 485 |
"content": "<extra_id_44>",
|
| 486 |
"lstrip": true,
|
| 487 |
"normalized": true,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"single_word": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
-
|
| 493 |
"content": "<extra_id_43>",
|
| 494 |
"lstrip": true,
|
| 495 |
"normalized": true,
|
| 496 |
"rstrip": false,
|
| 497 |
-
"single_word": false
|
| 498 |
-
"special": true
|
| 499 |
},
|
| 500 |
-
|
| 501 |
"content": "<extra_id_42>",
|
| 502 |
"lstrip": true,
|
| 503 |
"normalized": true,
|
| 504 |
"rstrip": false,
|
| 505 |
-
"single_word": false
|
| 506 |
-
"special": true
|
| 507 |
},
|
| 508 |
-
|
| 509 |
"content": "<extra_id_41>",
|
| 510 |
"lstrip": true,
|
| 511 |
"normalized": true,
|
| 512 |
"rstrip": false,
|
| 513 |
-
"single_word": false
|
| 514 |
-
"special": true
|
| 515 |
},
|
| 516 |
-
|
| 517 |
"content": "<extra_id_40>",
|
| 518 |
"lstrip": true,
|
| 519 |
"normalized": true,
|
| 520 |
"rstrip": false,
|
| 521 |
-
"single_word": false
|
| 522 |
-
"special": true
|
| 523 |
},
|
| 524 |
-
|
| 525 |
"content": "<extra_id_39>",
|
| 526 |
"lstrip": true,
|
| 527 |
"normalized": true,
|
| 528 |
"rstrip": false,
|
| 529 |
-
"single_word": false
|
| 530 |
-
"special": true
|
| 531 |
},
|
| 532 |
-
|
| 533 |
"content": "<extra_id_38>",
|
| 534 |
"lstrip": true,
|
| 535 |
"normalized": true,
|
| 536 |
"rstrip": false,
|
| 537 |
-
"single_word": false
|
| 538 |
-
"special": true
|
| 539 |
},
|
| 540 |
-
|
| 541 |
"content": "<extra_id_37>",
|
| 542 |
"lstrip": true,
|
| 543 |
"normalized": true,
|
| 544 |
"rstrip": false,
|
| 545 |
-
"single_word": false
|
| 546 |
-
"special": true
|
| 547 |
},
|
| 548 |
-
|
| 549 |
"content": "<extra_id_36>",
|
| 550 |
"lstrip": true,
|
| 551 |
"normalized": true,
|
| 552 |
"rstrip": false,
|
| 553 |
-
"single_word": false
|
| 554 |
-
"special": true
|
| 555 |
},
|
| 556 |
-
|
| 557 |
"content": "<extra_id_35>",
|
| 558 |
"lstrip": true,
|
| 559 |
"normalized": true,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"single_word": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
-
|
| 565 |
"content": "<extra_id_34>",
|
| 566 |
"lstrip": true,
|
| 567 |
"normalized": true,
|
| 568 |
"rstrip": false,
|
| 569 |
-
"single_word": false
|
| 570 |
-
"special": true
|
| 571 |
},
|
| 572 |
-
|
| 573 |
"content": "<extra_id_33>",
|
| 574 |
"lstrip": true,
|
| 575 |
"normalized": true,
|
| 576 |
"rstrip": false,
|
| 577 |
-
"single_word": false
|
| 578 |
-
"special": true
|
| 579 |
},
|
| 580 |
-
|
| 581 |
"content": "<extra_id_32>",
|
| 582 |
"lstrip": true,
|
| 583 |
"normalized": true,
|
| 584 |
"rstrip": false,
|
| 585 |
-
"single_word": false
|
| 586 |
-
"special": true
|
| 587 |
},
|
| 588 |
-
|
| 589 |
"content": "<extra_id_31>",
|
| 590 |
"lstrip": true,
|
| 591 |
"normalized": true,
|
| 592 |
"rstrip": false,
|
| 593 |
-
"single_word": false
|
| 594 |
-
"special": true
|
| 595 |
},
|
| 596 |
-
|
| 597 |
"content": "<extra_id_30>",
|
| 598 |
"lstrip": true,
|
| 599 |
"normalized": true,
|
| 600 |
"rstrip": false,
|
| 601 |
-
"single_word": false
|
| 602 |
-
"special": true
|
| 603 |
},
|
| 604 |
-
|
| 605 |
"content": "<extra_id_29>",
|
| 606 |
"lstrip": true,
|
| 607 |
"normalized": true,
|
| 608 |
"rstrip": false,
|
| 609 |
-
"single_word": false
|
| 610 |
-
"special": true
|
| 611 |
},
|
| 612 |
-
|
| 613 |
"content": "<extra_id_28>",
|
| 614 |
"lstrip": true,
|
| 615 |
"normalized": true,
|
| 616 |
"rstrip": false,
|
| 617 |
-
"single_word": false
|
| 618 |
-
"special": true
|
| 619 |
},
|
| 620 |
-
|
| 621 |
"content": "<extra_id_27>",
|
| 622 |
"lstrip": true,
|
| 623 |
"normalized": true,
|
| 624 |
"rstrip": false,
|
| 625 |
-
"single_word": false
|
| 626 |
-
"special": true
|
| 627 |
},
|
| 628 |
-
|
| 629 |
"content": "<extra_id_26>",
|
| 630 |
"lstrip": true,
|
| 631 |
"normalized": true,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"single_word": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
-
|
| 637 |
"content": "<extra_id_25>",
|
| 638 |
"lstrip": true,
|
| 639 |
"normalized": true,
|
| 640 |
"rstrip": false,
|
| 641 |
-
"single_word": false
|
| 642 |
-
"special": true
|
| 643 |
},
|
| 644 |
-
|
| 645 |
"content": "<extra_id_24>",
|
| 646 |
"lstrip": true,
|
| 647 |
"normalized": true,
|
| 648 |
"rstrip": false,
|
| 649 |
-
"single_word": false
|
| 650 |
-
"special": true
|
| 651 |
},
|
| 652 |
-
|
| 653 |
"content": "<extra_id_23>",
|
| 654 |
"lstrip": true,
|
| 655 |
"normalized": true,
|
| 656 |
"rstrip": false,
|
| 657 |
-
"single_word": false
|
| 658 |
-
"special": true
|
| 659 |
},
|
| 660 |
-
|
| 661 |
"content": "<extra_id_22>",
|
| 662 |
"lstrip": true,
|
| 663 |
"normalized": true,
|
| 664 |
"rstrip": false,
|
| 665 |
-
"single_word": false
|
| 666 |
-
"special": true
|
| 667 |
},
|
| 668 |
-
|
| 669 |
"content": "<extra_id_21>",
|
| 670 |
"lstrip": true,
|
| 671 |
"normalized": true,
|
| 672 |
"rstrip": false,
|
| 673 |
-
"single_word": false
|
| 674 |
-
"special": true
|
| 675 |
},
|
| 676 |
-
|
| 677 |
"content": "<extra_id_20>",
|
| 678 |
"lstrip": true,
|
| 679 |
"normalized": true,
|
| 680 |
"rstrip": false,
|
| 681 |
-
"single_word": false
|
| 682 |
-
"special": true
|
| 683 |
},
|
| 684 |
-
|
| 685 |
"content": "<extra_id_19>",
|
| 686 |
"lstrip": true,
|
| 687 |
"normalized": true,
|
| 688 |
"rstrip": false,
|
| 689 |
-
"single_word": false
|
| 690 |
-
"special": true
|
| 691 |
},
|
| 692 |
-
|
| 693 |
"content": "<extra_id_18>",
|
| 694 |
"lstrip": true,
|
| 695 |
"normalized": true,
|
| 696 |
"rstrip": false,
|
| 697 |
-
"single_word": false
|
| 698 |
-
"special": true
|
| 699 |
},
|
| 700 |
-
|
| 701 |
"content": "<extra_id_17>",
|
| 702 |
"lstrip": true,
|
| 703 |
"normalized": true,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"single_word": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
-
|
| 709 |
"content": "<extra_id_16>",
|
| 710 |
"lstrip": true,
|
| 711 |
"normalized": true,
|
| 712 |
"rstrip": false,
|
| 713 |
-
"single_word": false
|
| 714 |
-
"special": true
|
| 715 |
},
|
| 716 |
-
|
| 717 |
"content": "<extra_id_15>",
|
| 718 |
"lstrip": true,
|
| 719 |
"normalized": true,
|
| 720 |
"rstrip": false,
|
| 721 |
-
"single_word": false
|
| 722 |
-
"special": true
|
| 723 |
},
|
| 724 |
-
|
| 725 |
"content": "<extra_id_14>",
|
| 726 |
"lstrip": true,
|
| 727 |
"normalized": true,
|
| 728 |
"rstrip": false,
|
| 729 |
-
"single_word": false
|
| 730 |
-
"special": true
|
| 731 |
},
|
| 732 |
-
|
| 733 |
"content": "<extra_id_13>",
|
| 734 |
"lstrip": true,
|
| 735 |
"normalized": true,
|
| 736 |
"rstrip": false,
|
| 737 |
-
"single_word": false
|
| 738 |
-
"special": true
|
| 739 |
},
|
| 740 |
-
|
| 741 |
"content": "<extra_id_12>",
|
| 742 |
"lstrip": true,
|
| 743 |
"normalized": true,
|
| 744 |
"rstrip": false,
|
| 745 |
-
"single_word": false
|
| 746 |
-
"special": true
|
| 747 |
},
|
| 748 |
-
|
| 749 |
"content": "<extra_id_11>",
|
| 750 |
"lstrip": true,
|
| 751 |
"normalized": true,
|
| 752 |
"rstrip": false,
|
| 753 |
-
"single_word": false
|
| 754 |
-
"special": true
|
| 755 |
},
|
| 756 |
-
|
| 757 |
"content": "<extra_id_10>",
|
| 758 |
"lstrip": true,
|
| 759 |
"normalized": true,
|
| 760 |
"rstrip": false,
|
| 761 |
-
"single_word": false
|
| 762 |
-
"special": true
|
| 763 |
},
|
| 764 |
-
|
| 765 |
"content": "<extra_id_9>",
|
| 766 |
"lstrip": true,
|
| 767 |
"normalized": true,
|
| 768 |
"rstrip": false,
|
| 769 |
-
"single_word": false
|
| 770 |
-
"special": true
|
| 771 |
},
|
| 772 |
-
|
| 773 |
"content": "<extra_id_8>",
|
| 774 |
"lstrip": true,
|
| 775 |
"normalized": true,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"single_word": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
-
|
| 781 |
"content": "<extra_id_7>",
|
| 782 |
"lstrip": true,
|
| 783 |
"normalized": true,
|
| 784 |
"rstrip": false,
|
| 785 |
-
"single_word": false
|
| 786 |
-
"special": true
|
| 787 |
},
|
| 788 |
-
|
| 789 |
"content": "<extra_id_6>",
|
| 790 |
"lstrip": true,
|
| 791 |
"normalized": true,
|
| 792 |
"rstrip": false,
|
| 793 |
-
"single_word": false
|
| 794 |
-
"special": true
|
| 795 |
},
|
| 796 |
-
|
| 797 |
"content": "<extra_id_5>",
|
| 798 |
"lstrip": true,
|
| 799 |
"normalized": true,
|
| 800 |
"rstrip": false,
|
| 801 |
-
"single_word": false
|
| 802 |
-
"special": true
|
| 803 |
},
|
| 804 |
-
|
| 805 |
"content": "<extra_id_4>",
|
| 806 |
"lstrip": true,
|
| 807 |
"normalized": true,
|
| 808 |
"rstrip": false,
|
| 809 |
-
"single_word": false
|
| 810 |
-
"special": true
|
| 811 |
},
|
| 812 |
-
|
| 813 |
"content": "<extra_id_3>",
|
| 814 |
"lstrip": true,
|
| 815 |
"normalized": true,
|
| 816 |
"rstrip": false,
|
| 817 |
-
"single_word": false
|
| 818 |
-
"special": true
|
| 819 |
},
|
| 820 |
-
|
| 821 |
"content": "<extra_id_2>",
|
| 822 |
"lstrip": true,
|
| 823 |
"normalized": true,
|
| 824 |
"rstrip": false,
|
| 825 |
-
"single_word": false
|
| 826 |
-
"special": true
|
| 827 |
},
|
| 828 |
-
|
| 829 |
"content": "<extra_id_1>",
|
| 830 |
"lstrip": true,
|
| 831 |
"normalized": true,
|
| 832 |
"rstrip": false,
|
| 833 |
-
"single_word": false
|
| 834 |
-
"special": true
|
| 835 |
},
|
| 836 |
-
|
| 837 |
"content": "<extra_id_0>",
|
| 838 |
"lstrip": true,
|
| 839 |
"normalized": true,
|
| 840 |
"rstrip": false,
|
| 841 |
-
"single_word": false
|
| 842 |
-
"special": true
|
| 843 |
}
|
| 844 |
-
},
|
| 845 |
-
"additional_special_tokens": [
|
| 846 |
-
"<extra_id_99>",
|
| 847 |
-
"<extra_id_98>",
|
| 848 |
-
"<extra_id_97>",
|
| 849 |
-
"<extra_id_96>",
|
| 850 |
-
"<extra_id_95>",
|
| 851 |
-
"<extra_id_94>",
|
| 852 |
-
"<extra_id_93>",
|
| 853 |
-
"<extra_id_92>",
|
| 854 |
-
"<extra_id_91>",
|
| 855 |
-
"<extra_id_90>",
|
| 856 |
-
"<extra_id_89>",
|
| 857 |
-
"<extra_id_88>",
|
| 858 |
-
"<extra_id_87>",
|
| 859 |
-
"<extra_id_86>",
|
| 860 |
-
"<extra_id_85>",
|
| 861 |
-
"<extra_id_84>",
|
| 862 |
-
"<extra_id_83>",
|
| 863 |
-
"<extra_id_82>",
|
| 864 |
-
"<extra_id_81>",
|
| 865 |
-
"<extra_id_80>",
|
| 866 |
-
"<extra_id_79>",
|
| 867 |
-
"<extra_id_78>",
|
| 868 |
-
"<extra_id_77>",
|
| 869 |
-
"<extra_id_76>",
|
| 870 |
-
"<extra_id_75>",
|
| 871 |
-
"<extra_id_74>",
|
| 872 |
-
"<extra_id_73>",
|
| 873 |
-
"<extra_id_72>",
|
| 874 |
-
"<extra_id_71>",
|
| 875 |
-
"<extra_id_70>",
|
| 876 |
-
"<extra_id_69>",
|
| 877 |
-
"<extra_id_68>",
|
| 878 |
-
"<extra_id_67>",
|
| 879 |
-
"<extra_id_66>",
|
| 880 |
-
"<extra_id_65>",
|
| 881 |
-
"<extra_id_64>",
|
| 882 |
-
"<extra_id_63>",
|
| 883 |
-
"<extra_id_62>",
|
| 884 |
-
"<extra_id_61>",
|
| 885 |
-
"<extra_id_60>",
|
| 886 |
-
"<extra_id_59>",
|
| 887 |
-
"<extra_id_58>",
|
| 888 |
-
"<extra_id_57>",
|
| 889 |
-
"<extra_id_56>",
|
| 890 |
-
"<extra_id_55>",
|
| 891 |
-
"<extra_id_54>",
|
| 892 |
-
"<extra_id_53>",
|
| 893 |
-
"<extra_id_52>",
|
| 894 |
-
"<extra_id_51>",
|
| 895 |
-
"<extra_id_50>",
|
| 896 |
-
"<extra_id_49>",
|
| 897 |
-
"<extra_id_48>",
|
| 898 |
-
"<extra_id_47>",
|
| 899 |
-
"<extra_id_46>",
|
| 900 |
-
"<extra_id_45>",
|
| 901 |
-
"<extra_id_44>",
|
| 902 |
-
"<extra_id_43>",
|
| 903 |
-
"<extra_id_42>",
|
| 904 |
-
"<extra_id_41>",
|
| 905 |
-
"<extra_id_40>",
|
| 906 |
-
"<extra_id_39>",
|
| 907 |
-
"<extra_id_38>",
|
| 908 |
-
"<extra_id_37>",
|
| 909 |
-
"<extra_id_36>",
|
| 910 |
-
"<extra_id_35>",
|
| 911 |
-
"<extra_id_34>",
|
| 912 |
-
"<extra_id_33>",
|
| 913 |
-
"<extra_id_32>",
|
| 914 |
-
"<extra_id_31>",
|
| 915 |
-
"<extra_id_30>",
|
| 916 |
-
"<extra_id_29>",
|
| 917 |
-
"<extra_id_28>",
|
| 918 |
-
"<extra_id_27>",
|
| 919 |
-
"<extra_id_26>",
|
| 920 |
-
"<extra_id_25>",
|
| 921 |
-
"<extra_id_24>",
|
| 922 |
-
"<extra_id_23>",
|
| 923 |
-
"<extra_id_22>",
|
| 924 |
-
"<extra_id_21>",
|
| 925 |
-
"<extra_id_20>",
|
| 926 |
-
"<extra_id_19>",
|
| 927 |
-
"<extra_id_18>",
|
| 928 |
-
"<extra_id_17>",
|
| 929 |
-
"<extra_id_16>",
|
| 930 |
-
"<extra_id_15>",
|
| 931 |
-
"<extra_id_14>",
|
| 932 |
-
"<extra_id_13>",
|
| 933 |
-
"<extra_id_12>",
|
| 934 |
-
"<extra_id_11>",
|
| 935 |
-
"<extra_id_10>",
|
| 936 |
-
"<extra_id_9>",
|
| 937 |
-
"<extra_id_8>",
|
| 938 |
-
"<extra_id_7>",
|
| 939 |
-
"<extra_id_6>",
|
| 940 |
-
"<extra_id_5>",
|
| 941 |
-
"<extra_id_4>",
|
| 942 |
-
"<extra_id_3>",
|
| 943 |
-
"<extra_id_2>",
|
| 944 |
-
"<extra_id_1>",
|
| 945 |
-
"<extra_id_0>"
|
| 946 |
],
|
|
|
|
| 947 |
"bos_token": "<s>",
|
| 948 |
-
"clean_up_tokenization_spaces": false,
|
| 949 |
"cls_token": "<s>",
|
| 950 |
"eos_token": "</s>",
|
| 951 |
"errors": "replace",
|
| 952 |
-
"extra_special_tokens":
|
|
|
|
| 953 |
"mask_token": "<mask>",
|
| 954 |
"model_max_length": 512,
|
| 955 |
"pad_token": "<pad>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"additional_special_tokens": [
|
| 4 |
+
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"content": "<extra_id_99>",
|
| 6 |
"lstrip": true,
|
| 7 |
"normalized": true,
|
| 8 |
"rstrip": false,
|
| 9 |
+
"single_word": false
|
|
|
|
| 10 |
},
|
| 11 |
+
{
|
| 12 |
"content": "<extra_id_98>",
|
| 13 |
"lstrip": true,
|
| 14 |
"normalized": true,
|
| 15 |
"rstrip": false,
|
| 16 |
+
"single_word": false
|
|
|
|
| 17 |
},
|
| 18 |
+
{
|
| 19 |
"content": "<extra_id_97>",
|
| 20 |
"lstrip": true,
|
| 21 |
"normalized": true,
|
| 22 |
"rstrip": false,
|
| 23 |
+
"single_word": false
|
|
|
|
| 24 |
},
|
| 25 |
+
{
|
| 26 |
"content": "<extra_id_96>",
|
| 27 |
"lstrip": true,
|
| 28 |
"normalized": true,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"single_word": false
|
|
|
|
| 31 |
},
|
| 32 |
+
{
|
| 33 |
"content": "<extra_id_95>",
|
| 34 |
"lstrip": true,
|
| 35 |
"normalized": true,
|
| 36 |
"rstrip": false,
|
| 37 |
+
"single_word": false
|
|
|
|
| 38 |
},
|
| 39 |
+
{
|
| 40 |
"content": "<extra_id_94>",
|
| 41 |
"lstrip": true,
|
| 42 |
"normalized": true,
|
| 43 |
"rstrip": false,
|
| 44 |
+
"single_word": false
|
|
|
|
| 45 |
},
|
| 46 |
+
{
|
| 47 |
"content": "<extra_id_93>",
|
| 48 |
"lstrip": true,
|
| 49 |
"normalized": true,
|
| 50 |
"rstrip": false,
|
| 51 |
+
"single_word": false
|
|
|
|
| 52 |
},
|
| 53 |
+
{
|
| 54 |
"content": "<extra_id_92>",
|
| 55 |
"lstrip": true,
|
| 56 |
"normalized": true,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"single_word": false
|
|
|
|
| 59 |
},
|
| 60 |
+
{
|
| 61 |
"content": "<extra_id_91>",
|
| 62 |
"lstrip": true,
|
| 63 |
"normalized": true,
|
| 64 |
"rstrip": false,
|
| 65 |
+
"single_word": false
|
|
|
|
| 66 |
},
|
| 67 |
+
{
|
| 68 |
"content": "<extra_id_90>",
|
| 69 |
"lstrip": true,
|
| 70 |
"normalized": true,
|
| 71 |
"rstrip": false,
|
| 72 |
+
"single_word": false
|
|
|
|
| 73 |
},
|
| 74 |
+
{
|
| 75 |
"content": "<extra_id_89>",
|
| 76 |
"lstrip": true,
|
| 77 |
"normalized": true,
|
| 78 |
"rstrip": false,
|
| 79 |
+
"single_word": false
|
|
|
|
| 80 |
},
|
| 81 |
+
{
|
| 82 |
"content": "<extra_id_88>",
|
| 83 |
"lstrip": true,
|
| 84 |
"normalized": true,
|
| 85 |
"rstrip": false,
|
| 86 |
+
"single_word": false
|
|
|
|
| 87 |
},
|
| 88 |
+
{
|
| 89 |
"content": "<extra_id_87>",
|
| 90 |
"lstrip": true,
|
| 91 |
"normalized": true,
|
| 92 |
"rstrip": false,
|
| 93 |
+
"single_word": false
|
|
|
|
| 94 |
},
|
| 95 |
+
{
|
| 96 |
"content": "<extra_id_86>",
|
| 97 |
"lstrip": true,
|
| 98 |
"normalized": true,
|
| 99 |
"rstrip": false,
|
| 100 |
+
"single_word": false
|
|
|
|
| 101 |
},
|
| 102 |
+
{
|
| 103 |
"content": "<extra_id_85>",
|
| 104 |
"lstrip": true,
|
| 105 |
"normalized": true,
|
| 106 |
"rstrip": false,
|
| 107 |
+
"single_word": false
|
|
|
|
| 108 |
},
|
| 109 |
+
{
|
| 110 |
"content": "<extra_id_84>",
|
| 111 |
"lstrip": true,
|
| 112 |
"normalized": true,
|
| 113 |
"rstrip": false,
|
| 114 |
+
"single_word": false
|
|
|
|
| 115 |
},
|
| 116 |
+
{
|
| 117 |
"content": "<extra_id_83>",
|
| 118 |
"lstrip": true,
|
| 119 |
"normalized": true,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"single_word": false
|
|
|
|
| 122 |
},
|
| 123 |
+
{
|
| 124 |
"content": "<extra_id_82>",
|
| 125 |
"lstrip": true,
|
| 126 |
"normalized": true,
|
| 127 |
"rstrip": false,
|
| 128 |
+
"single_word": false
|
|
|
|
| 129 |
},
|
| 130 |
+
{
|
| 131 |
"content": "<extra_id_81>",
|
| 132 |
"lstrip": true,
|
| 133 |
"normalized": true,
|
| 134 |
"rstrip": false,
|
| 135 |
+
"single_word": false
|
|
|
|
| 136 |
},
|
| 137 |
+
{
|
| 138 |
"content": "<extra_id_80>",
|
| 139 |
"lstrip": true,
|
| 140 |
"normalized": true,
|
| 141 |
"rstrip": false,
|
| 142 |
+
"single_word": false
|
|
|
|
| 143 |
},
|
| 144 |
+
{
|
| 145 |
"content": "<extra_id_79>",
|
| 146 |
"lstrip": true,
|
| 147 |
"normalized": true,
|
| 148 |
"rstrip": false,
|
| 149 |
+
"single_word": false
|
|
|
|
| 150 |
},
|
| 151 |
+
{
|
| 152 |
"content": "<extra_id_78>",
|
| 153 |
"lstrip": true,
|
| 154 |
"normalized": true,
|
| 155 |
"rstrip": false,
|
| 156 |
+
"single_word": false
|
|
|
|
| 157 |
},
|
| 158 |
+
{
|
| 159 |
"content": "<extra_id_77>",
|
| 160 |
"lstrip": true,
|
| 161 |
"normalized": true,
|
| 162 |
"rstrip": false,
|
| 163 |
+
"single_word": false
|
|
|
|
| 164 |
},
|
| 165 |
+
{
|
| 166 |
"content": "<extra_id_76>",
|
| 167 |
"lstrip": true,
|
| 168 |
"normalized": true,
|
| 169 |
"rstrip": false,
|
| 170 |
+
"single_word": false
|
|
|
|
| 171 |
},
|
| 172 |
+
{
|
| 173 |
"content": "<extra_id_75>",
|
| 174 |
"lstrip": true,
|
| 175 |
"normalized": true,
|
| 176 |
"rstrip": false,
|
| 177 |
+
"single_word": false
|
|
|
|
| 178 |
},
|
| 179 |
+
{
|
| 180 |
"content": "<extra_id_74>",
|
| 181 |
"lstrip": true,
|
| 182 |
"normalized": true,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"single_word": false
|
|
|
|
| 185 |
},
|
| 186 |
+
{
|
| 187 |
"content": "<extra_id_73>",
|
| 188 |
"lstrip": true,
|
| 189 |
"normalized": true,
|
| 190 |
"rstrip": false,
|
| 191 |
+
"single_word": false
|
|
|
|
| 192 |
},
|
| 193 |
+
{
|
| 194 |
"content": "<extra_id_72>",
|
| 195 |
"lstrip": true,
|
| 196 |
"normalized": true,
|
| 197 |
"rstrip": false,
|
| 198 |
+
"single_word": false
|
|
|
|
| 199 |
},
|
| 200 |
+
{
|
| 201 |
"content": "<extra_id_71>",
|
| 202 |
"lstrip": true,
|
| 203 |
"normalized": true,
|
| 204 |
"rstrip": false,
|
| 205 |
+
"single_word": false
|
|
|
|
| 206 |
},
|
| 207 |
+
{
|
| 208 |
"content": "<extra_id_70>",
|
| 209 |
"lstrip": true,
|
| 210 |
"normalized": true,
|
| 211 |
"rstrip": false,
|
| 212 |
+
"single_word": false
|
|
|
|
| 213 |
},
|
| 214 |
+
{
|
| 215 |
"content": "<extra_id_69>",
|
| 216 |
"lstrip": true,
|
| 217 |
"normalized": true,
|
| 218 |
"rstrip": false,
|
| 219 |
+
"single_word": false
|
|
|
|
| 220 |
},
|
| 221 |
+
{
|
| 222 |
"content": "<extra_id_68>",
|
| 223 |
"lstrip": true,
|
| 224 |
"normalized": true,
|
| 225 |
"rstrip": false,
|
| 226 |
+
"single_word": false
|
|
|
|
| 227 |
},
|
| 228 |
+
{
|
| 229 |
"content": "<extra_id_67>",
|
| 230 |
"lstrip": true,
|
| 231 |
"normalized": true,
|
| 232 |
"rstrip": false,
|
| 233 |
+
"single_word": false
|
|
|
|
| 234 |
},
|
| 235 |
+
{
|
| 236 |
"content": "<extra_id_66>",
|
| 237 |
"lstrip": true,
|
| 238 |
"normalized": true,
|
| 239 |
"rstrip": false,
|
| 240 |
+
"single_word": false
|
|
|
|
| 241 |
},
|
| 242 |
+
{
|
| 243 |
"content": "<extra_id_65>",
|
| 244 |
"lstrip": true,
|
| 245 |
"normalized": true,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"single_word": false
|
|
|
|
| 248 |
},
|
| 249 |
+
{
|
| 250 |
"content": "<extra_id_64>",
|
| 251 |
"lstrip": true,
|
| 252 |
"normalized": true,
|
| 253 |
"rstrip": false,
|
| 254 |
+
"single_word": false
|
|
|
|
| 255 |
},
|
| 256 |
+
{
|
| 257 |
"content": "<extra_id_63>",
|
| 258 |
"lstrip": true,
|
| 259 |
"normalized": true,
|
| 260 |
"rstrip": false,
|
| 261 |
+
"single_word": false
|
|
|
|
| 262 |
},
|
| 263 |
+
{
|
| 264 |
"content": "<extra_id_62>",
|
| 265 |
"lstrip": true,
|
| 266 |
"normalized": true,
|
| 267 |
"rstrip": false,
|
| 268 |
+
"single_word": false
|
|
|
|
| 269 |
},
|
| 270 |
+
{
|
| 271 |
"content": "<extra_id_61>",
|
| 272 |
"lstrip": true,
|
| 273 |
"normalized": true,
|
| 274 |
"rstrip": false,
|
| 275 |
+
"single_word": false
|
|
|
|
| 276 |
},
|
| 277 |
+
{
|
| 278 |
"content": "<extra_id_60>",
|
| 279 |
"lstrip": true,
|
| 280 |
"normalized": true,
|
| 281 |
"rstrip": false,
|
| 282 |
+
"single_word": false
|
|
|
|
| 283 |
},
|
| 284 |
+
{
|
| 285 |
"content": "<extra_id_59>",
|
| 286 |
"lstrip": true,
|
| 287 |
"normalized": true,
|
| 288 |
"rstrip": false,
|
| 289 |
+
"single_word": false
|
|
|
|
| 290 |
},
|
| 291 |
+
{
|
| 292 |
"content": "<extra_id_58>",
|
| 293 |
"lstrip": true,
|
| 294 |
"normalized": true,
|
| 295 |
"rstrip": false,
|
| 296 |
+
"single_word": false
|
|
|
|
| 297 |
},
|
| 298 |
+
{
|
| 299 |
"content": "<extra_id_57>",
|
| 300 |
"lstrip": true,
|
| 301 |
"normalized": true,
|
| 302 |
"rstrip": false,
|
| 303 |
+
"single_word": false
|
|
|
|
| 304 |
},
|
| 305 |
+
{
|
| 306 |
"content": "<extra_id_56>",
|
| 307 |
"lstrip": true,
|
| 308 |
"normalized": true,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"single_word": false
|
|
|
|
| 311 |
},
|
| 312 |
+
{
|
| 313 |
"content": "<extra_id_55>",
|
| 314 |
"lstrip": true,
|
| 315 |
"normalized": true,
|
| 316 |
"rstrip": false,
|
| 317 |
+
"single_word": false
|
|
|
|
| 318 |
},
|
| 319 |
+
{
|
| 320 |
"content": "<extra_id_54>",
|
| 321 |
"lstrip": true,
|
| 322 |
"normalized": true,
|
| 323 |
"rstrip": false,
|
| 324 |
+
"single_word": false
|
|
|
|
| 325 |
},
|
| 326 |
+
{
|
| 327 |
"content": "<extra_id_53>",
|
| 328 |
"lstrip": true,
|
| 329 |
"normalized": true,
|
| 330 |
"rstrip": false,
|
| 331 |
+
"single_word": false
|
|
|
|
| 332 |
},
|
| 333 |
+
{
|
| 334 |
"content": "<extra_id_52>",
|
| 335 |
"lstrip": true,
|
| 336 |
"normalized": true,
|
| 337 |
"rstrip": false,
|
| 338 |
+
"single_word": false
|
|
|
|
| 339 |
},
|
| 340 |
+
{
|
| 341 |
"content": "<extra_id_51>",
|
| 342 |
"lstrip": true,
|
| 343 |
"normalized": true,
|
| 344 |
"rstrip": false,
|
| 345 |
+
"single_word": false
|
|
|
|
| 346 |
},
|
| 347 |
+
{
|
| 348 |
"content": "<extra_id_50>",
|
| 349 |
"lstrip": true,
|
| 350 |
"normalized": true,
|
| 351 |
"rstrip": false,
|
| 352 |
+
"single_word": false
|
|
|
|
| 353 |
},
|
| 354 |
+
{
|
| 355 |
"content": "<extra_id_49>",
|
| 356 |
"lstrip": true,
|
| 357 |
"normalized": true,
|
| 358 |
"rstrip": false,
|
| 359 |
+
"single_word": false
|
|
|
|
| 360 |
},
|
| 361 |
+
{
|
| 362 |
"content": "<extra_id_48>",
|
| 363 |
"lstrip": true,
|
| 364 |
"normalized": true,
|
| 365 |
"rstrip": false,
|
| 366 |
+
"single_word": false
|
|
|
|
| 367 |
},
|
| 368 |
+
{
|
| 369 |
"content": "<extra_id_47>",
|
| 370 |
"lstrip": true,
|
| 371 |
"normalized": true,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"single_word": false
|
|
|
|
| 374 |
},
|
| 375 |
+
{
|
| 376 |
"content": "<extra_id_46>",
|
| 377 |
"lstrip": true,
|
| 378 |
"normalized": true,
|
| 379 |
"rstrip": false,
|
| 380 |
+
"single_word": false
|
|
|
|
| 381 |
},
|
| 382 |
+
{
|
| 383 |
"content": "<extra_id_45>",
|
| 384 |
"lstrip": true,
|
| 385 |
"normalized": true,
|
| 386 |
"rstrip": false,
|
| 387 |
+
"single_word": false
|
|
|
|
| 388 |
},
|
| 389 |
+
{
|
| 390 |
"content": "<extra_id_44>",
|
| 391 |
"lstrip": true,
|
| 392 |
"normalized": true,
|
| 393 |
"rstrip": false,
|
| 394 |
+
"single_word": false
|
|
|
|
| 395 |
},
|
| 396 |
+
{
|
| 397 |
"content": "<extra_id_43>",
|
| 398 |
"lstrip": true,
|
| 399 |
"normalized": true,
|
| 400 |
"rstrip": false,
|
| 401 |
+
"single_word": false
|
|
|
|
| 402 |
},
|
| 403 |
+
{
|
| 404 |
"content": "<extra_id_42>",
|
| 405 |
"lstrip": true,
|
| 406 |
"normalized": true,
|
| 407 |
"rstrip": false,
|
| 408 |
+
"single_word": false
|
|
|
|
| 409 |
},
|
| 410 |
+
{
|
| 411 |
"content": "<extra_id_41>",
|
| 412 |
"lstrip": true,
|
| 413 |
"normalized": true,
|
| 414 |
"rstrip": false,
|
| 415 |
+
"single_word": false
|
|
|
|
| 416 |
},
|
| 417 |
+
{
|
| 418 |
"content": "<extra_id_40>",
|
| 419 |
"lstrip": true,
|
| 420 |
"normalized": true,
|
| 421 |
"rstrip": false,
|
| 422 |
+
"single_word": false
|
|
|
|
| 423 |
},
|
| 424 |
+
{
|
| 425 |
"content": "<extra_id_39>",
|
| 426 |
"lstrip": true,
|
| 427 |
"normalized": true,
|
| 428 |
"rstrip": false,
|
| 429 |
+
"single_word": false
|
|
|
|
| 430 |
},
|
| 431 |
+
{
|
| 432 |
"content": "<extra_id_38>",
|
| 433 |
"lstrip": true,
|
| 434 |
"normalized": true,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"single_word": false
|
|
|
|
| 437 |
},
|
| 438 |
+
{
|
| 439 |
"content": "<extra_id_37>",
|
| 440 |
"lstrip": true,
|
| 441 |
"normalized": true,
|
| 442 |
"rstrip": false,
|
| 443 |
+
"single_word": false
|
|
|
|
| 444 |
},
|
| 445 |
+
{
|
| 446 |
"content": "<extra_id_36>",
|
| 447 |
"lstrip": true,
|
| 448 |
"normalized": true,
|
| 449 |
"rstrip": false,
|
| 450 |
+
"single_word": false
|
|
|
|
| 451 |
},
|
| 452 |
+
{
|
| 453 |
"content": "<extra_id_35>",
|
| 454 |
"lstrip": true,
|
| 455 |
"normalized": true,
|
| 456 |
"rstrip": false,
|
| 457 |
+
"single_word": false
|
|
|
|
| 458 |
},
|
| 459 |
+
{
|
| 460 |
"content": "<extra_id_34>",
|
| 461 |
"lstrip": true,
|
| 462 |
"normalized": true,
|
| 463 |
"rstrip": false,
|
| 464 |
+
"single_word": false
|
|
|
|
| 465 |
},
|
| 466 |
+
{
|
| 467 |
"content": "<extra_id_33>",
|
| 468 |
"lstrip": true,
|
| 469 |
"normalized": true,
|
| 470 |
"rstrip": false,
|
| 471 |
+
"single_word": false
|
|
|
|
| 472 |
},
|
| 473 |
+
{
|
| 474 |
"content": "<extra_id_32>",
|
| 475 |
"lstrip": true,
|
| 476 |
"normalized": true,
|
| 477 |
"rstrip": false,
|
| 478 |
+
"single_word": false
|
|
|
|
| 479 |
},
|
| 480 |
+
{
|
| 481 |
"content": "<extra_id_31>",
|
| 482 |
"lstrip": true,
|
| 483 |
"normalized": true,
|
| 484 |
"rstrip": false,
|
| 485 |
+
"single_word": false
|
|
|
|
| 486 |
},
|
| 487 |
+
{
|
| 488 |
"content": "<extra_id_30>",
|
| 489 |
"lstrip": true,
|
| 490 |
"normalized": true,
|
| 491 |
"rstrip": false,
|
| 492 |
+
"single_word": false
|
|
|
|
| 493 |
},
|
| 494 |
+
{
|
| 495 |
"content": "<extra_id_29>",
|
| 496 |
"lstrip": true,
|
| 497 |
"normalized": true,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"single_word": false
|
|
|
|
| 500 |
},
|
| 501 |
+
{
|
| 502 |
"content": "<extra_id_28>",
|
| 503 |
"lstrip": true,
|
| 504 |
"normalized": true,
|
| 505 |
"rstrip": false,
|
| 506 |
+
"single_word": false
|
|
|
|
| 507 |
},
|
| 508 |
+
{
|
| 509 |
"content": "<extra_id_27>",
|
| 510 |
"lstrip": true,
|
| 511 |
"normalized": true,
|
| 512 |
"rstrip": false,
|
| 513 |
+
"single_word": false
|
|
|
|
| 514 |
},
|
| 515 |
+
{
|
| 516 |
"content": "<extra_id_26>",
|
| 517 |
"lstrip": true,
|
| 518 |
"normalized": true,
|
| 519 |
"rstrip": false,
|
| 520 |
+
"single_word": false
|
|
|
|
| 521 |
},
|
| 522 |
+
{
|
| 523 |
"content": "<extra_id_25>",
|
| 524 |
"lstrip": true,
|
| 525 |
"normalized": true,
|
| 526 |
"rstrip": false,
|
| 527 |
+
"single_word": false
|
|
|
|
| 528 |
},
|
| 529 |
+
{
|
| 530 |
"content": "<extra_id_24>",
|
| 531 |
"lstrip": true,
|
| 532 |
"normalized": true,
|
| 533 |
"rstrip": false,
|
| 534 |
+
"single_word": false
|
|
|
|
| 535 |
},
|
| 536 |
+
{
|
| 537 |
"content": "<extra_id_23>",
|
| 538 |
"lstrip": true,
|
| 539 |
"normalized": true,
|
| 540 |
"rstrip": false,
|
| 541 |
+
"single_word": false
|
|
|
|
| 542 |
},
|
| 543 |
+
{
|
| 544 |
"content": "<extra_id_22>",
|
| 545 |
"lstrip": true,
|
| 546 |
"normalized": true,
|
| 547 |
"rstrip": false,
|
| 548 |
+
"single_word": false
|
|
|
|
| 549 |
},
|
| 550 |
+
{
|
| 551 |
"content": "<extra_id_21>",
|
| 552 |
"lstrip": true,
|
| 553 |
"normalized": true,
|
| 554 |
"rstrip": false,
|
| 555 |
+
"single_word": false
|
|
|
|
| 556 |
},
|
| 557 |
+
{
|
| 558 |
"content": "<extra_id_20>",
|
| 559 |
"lstrip": true,
|
| 560 |
"normalized": true,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"single_word": false
|
|
|
|
| 563 |
},
|
| 564 |
+
{
|
| 565 |
"content": "<extra_id_19>",
|
| 566 |
"lstrip": true,
|
| 567 |
"normalized": true,
|
| 568 |
"rstrip": false,
|
| 569 |
+
"single_word": false
|
|
|
|
| 570 |
},
|
| 571 |
+
{
|
| 572 |
"content": "<extra_id_18>",
|
| 573 |
"lstrip": true,
|
| 574 |
"normalized": true,
|
| 575 |
"rstrip": false,
|
| 576 |
+
"single_word": false
|
|
|
|
| 577 |
},
|
| 578 |
+
{
|
| 579 |
"content": "<extra_id_17>",
|
| 580 |
"lstrip": true,
|
| 581 |
"normalized": true,
|
| 582 |
"rstrip": false,
|
| 583 |
+
"single_word": false
|
|
|
|
| 584 |
},
|
| 585 |
+
{
|
| 586 |
"content": "<extra_id_16>",
|
| 587 |
"lstrip": true,
|
| 588 |
"normalized": true,
|
| 589 |
"rstrip": false,
|
| 590 |
+
"single_word": false
|
|
|
|
| 591 |
},
|
| 592 |
+
{
|
| 593 |
"content": "<extra_id_15>",
|
| 594 |
"lstrip": true,
|
| 595 |
"normalized": true,
|
| 596 |
"rstrip": false,
|
| 597 |
+
"single_word": false
|
|
|
|
| 598 |
},
|
| 599 |
+
{
|
| 600 |
"content": "<extra_id_14>",
|
| 601 |
"lstrip": true,
|
| 602 |
"normalized": true,
|
| 603 |
"rstrip": false,
|
| 604 |
+
"single_word": false
|
|
|
|
| 605 |
},
|
| 606 |
+
{
|
| 607 |
"content": "<extra_id_13>",
|
| 608 |
"lstrip": true,
|
| 609 |
"normalized": true,
|
| 610 |
"rstrip": false,
|
| 611 |
+
"single_word": false
|
|
|
|
| 612 |
},
|
| 613 |
+
{
|
| 614 |
"content": "<extra_id_12>",
|
| 615 |
"lstrip": true,
|
| 616 |
"normalized": true,
|
| 617 |
"rstrip": false,
|
| 618 |
+
"single_word": false
|
|
|
|
| 619 |
},
|
| 620 |
+
{
|
| 621 |
"content": "<extra_id_11>",
|
| 622 |
"lstrip": true,
|
| 623 |
"normalized": true,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"single_word": false
|
|
|
|
| 626 |
},
|
| 627 |
+
{
|
| 628 |
"content": "<extra_id_10>",
|
| 629 |
"lstrip": true,
|
| 630 |
"normalized": true,
|
| 631 |
"rstrip": false,
|
| 632 |
+
"single_word": false
|
|
|
|
| 633 |
},
|
| 634 |
+
{
|
| 635 |
"content": "<extra_id_9>",
|
| 636 |
"lstrip": true,
|
| 637 |
"normalized": true,
|
| 638 |
"rstrip": false,
|
| 639 |
+
"single_word": false
|
|
|
|
| 640 |
},
|
| 641 |
+
{
|
| 642 |
"content": "<extra_id_8>",
|
| 643 |
"lstrip": true,
|
| 644 |
"normalized": true,
|
| 645 |
"rstrip": false,
|
| 646 |
+
"single_word": false
|
|
|
|
| 647 |
},
|
| 648 |
+
{
|
| 649 |
"content": "<extra_id_7>",
|
| 650 |
"lstrip": true,
|
| 651 |
"normalized": true,
|
| 652 |
"rstrip": false,
|
| 653 |
+
"single_word": false
|
|
|
|
| 654 |
},
|
| 655 |
+
{
|
| 656 |
"content": "<extra_id_6>",
|
| 657 |
"lstrip": true,
|
| 658 |
"normalized": true,
|
| 659 |
"rstrip": false,
|
| 660 |
+
"single_word": false
|
|
|
|
| 661 |
},
|
| 662 |
+
{
|
| 663 |
"content": "<extra_id_5>",
|
| 664 |
"lstrip": true,
|
| 665 |
"normalized": true,
|
| 666 |
"rstrip": false,
|
| 667 |
+
"single_word": false
|
|
|
|
| 668 |
},
|
| 669 |
+
{
|
| 670 |
"content": "<extra_id_4>",
|
| 671 |
"lstrip": true,
|
| 672 |
"normalized": true,
|
| 673 |
"rstrip": false,
|
| 674 |
+
"single_word": false
|
|
|
|
| 675 |
},
|
| 676 |
+
{
|
| 677 |
"content": "<extra_id_3>",
|
| 678 |
"lstrip": true,
|
| 679 |
"normalized": true,
|
| 680 |
"rstrip": false,
|
| 681 |
+
"single_word": false
|
|
|
|
| 682 |
},
|
| 683 |
+
{
|
| 684 |
"content": "<extra_id_2>",
|
| 685 |
"lstrip": true,
|
| 686 |
"normalized": true,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"single_word": false
|
|
|
|
| 689 |
},
|
| 690 |
+
{
|
| 691 |
"content": "<extra_id_1>",
|
| 692 |
"lstrip": true,
|
| 693 |
"normalized": true,
|
| 694 |
"rstrip": false,
|
| 695 |
+
"single_word": false
|
|
|
|
| 696 |
},
|
| 697 |
+
{
|
| 698 |
"content": "<extra_id_0>",
|
| 699 |
"lstrip": true,
|
| 700 |
"normalized": true,
|
| 701 |
"rstrip": false,
|
| 702 |
+
"single_word": false
|
|
|
|
| 703 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 704 |
],
|
| 705 |
+
"backend": "tokenizers",
|
| 706 |
"bos_token": "<s>",
|
|
|
|
| 707 |
"cls_token": "<s>",
|
| 708 |
"eos_token": "</s>",
|
| 709 |
"errors": "replace",
|
| 710 |
+
"extra_special_tokens": [],
|
| 711 |
+
"is_local": false,
|
| 712 |
"mask_token": "<mask>",
|
| 713 |
"model_max_length": 512,
|
| 714 |
"pad_token": "<pad>",
|