Upload 12 files
Browse files- .gitattributes +1 -0
- config.json +33 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +839 -0
- trainer_state.json +482 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "T5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.42.3",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 250112
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.42.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbdc2a67d1c3b33d515b48fe0692e4959b1a1138b2e9802e04cfd60ff8af1461
|
| 3 |
+
size 2329638768
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:408edc7dde38c9294493d63e7713f1110b1cbd23637c80c631ccf0906e11a910
|
| 3 |
+
size 4659448110
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c7e23ec201a7aed59751cc4f3169b1f663647712039cbe88a3dcefeb56b6b4b
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:205e723170d50d092525f34628b6bb4d90f46b773e7f7e412c3416c2067a0763
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde90e1c6efb1bffb6ac37b9b85a75465763ed4c4f48615ca4db3b069d5975de
|
| 3 |
+
size 16350085
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,839 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"250000": {
|
| 29 |
+
"content": "▁<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"250001": {
|
| 37 |
+
"content": "▁<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"250002": {
|
| 45 |
+
"content": "▁<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"250003": {
|
| 53 |
+
"content": "▁<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"250004": {
|
| 61 |
+
"content": "▁<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"250005": {
|
| 69 |
+
"content": "▁<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"250006": {
|
| 77 |
+
"content": "▁<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"250007": {
|
| 85 |
+
"content": "▁<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"250008": {
|
| 93 |
+
"content": "▁<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"250009": {
|
| 101 |
+
"content": "▁<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"250010": {
|
| 109 |
+
"content": "▁<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"250011": {
|
| 117 |
+
"content": "▁<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"250012": {
|
| 125 |
+
"content": "▁<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"250013": {
|
| 133 |
+
"content": "▁<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"250014": {
|
| 141 |
+
"content": "▁<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"250015": {
|
| 149 |
+
"content": "▁<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"250016": {
|
| 157 |
+
"content": "▁<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"250017": {
|
| 165 |
+
"content": "▁<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"250018": {
|
| 173 |
+
"content": "▁<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"250019": {
|
| 181 |
+
"content": "▁<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"250020": {
|
| 189 |
+
"content": "▁<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"250021": {
|
| 197 |
+
"content": "▁<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"250022": {
|
| 205 |
+
"content": "▁<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"250023": {
|
| 213 |
+
"content": "▁<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"250024": {
|
| 221 |
+
"content": "▁<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"250025": {
|
| 229 |
+
"content": "▁<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"250026": {
|
| 237 |
+
"content": "▁<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"250027": {
|
| 245 |
+
"content": "▁<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"250028": {
|
| 253 |
+
"content": "▁<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"250029": {
|
| 261 |
+
"content": "▁<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"250030": {
|
| 269 |
+
"content": "▁<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"250031": {
|
| 277 |
+
"content": "▁<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"250032": {
|
| 285 |
+
"content": "▁<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"250033": {
|
| 293 |
+
"content": "▁<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"250034": {
|
| 301 |
+
"content": "▁<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"250035": {
|
| 309 |
+
"content": "▁<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
},
|
| 316 |
+
"250036": {
|
| 317 |
+
"content": "▁<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": false
|
| 323 |
+
},
|
| 324 |
+
"250037": {
|
| 325 |
+
"content": "▁<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": false
|
| 331 |
+
},
|
| 332 |
+
"250038": {
|
| 333 |
+
"content": "▁<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": false
|
| 339 |
+
},
|
| 340 |
+
"250039": {
|
| 341 |
+
"content": "▁<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": false
|
| 347 |
+
},
|
| 348 |
+
"250040": {
|
| 349 |
+
"content": "▁<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": false
|
| 355 |
+
},
|
| 356 |
+
"250041": {
|
| 357 |
+
"content": "▁<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": false
|
| 363 |
+
},
|
| 364 |
+
"250042": {
|
| 365 |
+
"content": "▁<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": false
|
| 371 |
+
},
|
| 372 |
+
"250043": {
|
| 373 |
+
"content": "▁<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": false
|
| 379 |
+
},
|
| 380 |
+
"250044": {
|
| 381 |
+
"content": "▁<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": false
|
| 387 |
+
},
|
| 388 |
+
"250045": {
|
| 389 |
+
"content": "▁<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": false
|
| 395 |
+
},
|
| 396 |
+
"250046": {
|
| 397 |
+
"content": "▁<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": false
|
| 403 |
+
},
|
| 404 |
+
"250047": {
|
| 405 |
+
"content": "▁<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": false
|
| 411 |
+
},
|
| 412 |
+
"250048": {
|
| 413 |
+
"content": "▁<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": false
|
| 419 |
+
},
|
| 420 |
+
"250049": {
|
| 421 |
+
"content": "▁<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": false
|
| 427 |
+
},
|
| 428 |
+
"250050": {
|
| 429 |
+
"content": "���<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": false
|
| 435 |
+
},
|
| 436 |
+
"250051": {
|
| 437 |
+
"content": "▁<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": false
|
| 443 |
+
},
|
| 444 |
+
"250052": {
|
| 445 |
+
"content": "▁<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": false
|
| 451 |
+
},
|
| 452 |
+
"250053": {
|
| 453 |
+
"content": "▁<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": false
|
| 459 |
+
},
|
| 460 |
+
"250054": {
|
| 461 |
+
"content": "▁<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": false
|
| 467 |
+
},
|
| 468 |
+
"250055": {
|
| 469 |
+
"content": "▁<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": false
|
| 475 |
+
},
|
| 476 |
+
"250056": {
|
| 477 |
+
"content": "▁<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": false
|
| 483 |
+
},
|
| 484 |
+
"250057": {
|
| 485 |
+
"content": "▁<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": false
|
| 491 |
+
},
|
| 492 |
+
"250058": {
|
| 493 |
+
"content": "▁<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": false
|
| 499 |
+
},
|
| 500 |
+
"250059": {
|
| 501 |
+
"content": "▁<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": false
|
| 507 |
+
},
|
| 508 |
+
"250060": {
|
| 509 |
+
"content": "▁<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": false
|
| 515 |
+
},
|
| 516 |
+
"250061": {
|
| 517 |
+
"content": "▁<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": false
|
| 523 |
+
},
|
| 524 |
+
"250062": {
|
| 525 |
+
"content": "▁<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": false
|
| 531 |
+
},
|
| 532 |
+
"250063": {
|
| 533 |
+
"content": "▁<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": false
|
| 539 |
+
},
|
| 540 |
+
"250064": {
|
| 541 |
+
"content": "▁<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": false
|
| 547 |
+
},
|
| 548 |
+
"250065": {
|
| 549 |
+
"content": "▁<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": false
|
| 555 |
+
},
|
| 556 |
+
"250066": {
|
| 557 |
+
"content": "▁<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": false
|
| 563 |
+
},
|
| 564 |
+
"250067": {
|
| 565 |
+
"content": "▁<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": false
|
| 571 |
+
},
|
| 572 |
+
"250068": {
|
| 573 |
+
"content": "▁<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": false
|
| 579 |
+
},
|
| 580 |
+
"250069": {
|
| 581 |
+
"content": "▁<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": false
|
| 587 |
+
},
|
| 588 |
+
"250070": {
|
| 589 |
+
"content": "▁<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": false
|
| 595 |
+
},
|
| 596 |
+
"250071": {
|
| 597 |
+
"content": "▁<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": false
|
| 603 |
+
},
|
| 604 |
+
"250072": {
|
| 605 |
+
"content": "▁<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": false
|
| 611 |
+
},
|
| 612 |
+
"250073": {
|
| 613 |
+
"content": "▁<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": false
|
| 619 |
+
},
|
| 620 |
+
"250074": {
|
| 621 |
+
"content": "▁<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": false
|
| 627 |
+
},
|
| 628 |
+
"250075": {
|
| 629 |
+
"content": "▁<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": false
|
| 635 |
+
},
|
| 636 |
+
"250076": {
|
| 637 |
+
"content": "▁<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": false
|
| 643 |
+
},
|
| 644 |
+
"250077": {
|
| 645 |
+
"content": "▁<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": false
|
| 651 |
+
},
|
| 652 |
+
"250078": {
|
| 653 |
+
"content": "▁<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": false
|
| 659 |
+
},
|
| 660 |
+
"250079": {
|
| 661 |
+
"content": "▁<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": false
|
| 667 |
+
},
|
| 668 |
+
"250080": {
|
| 669 |
+
"content": "▁<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": false
|
| 675 |
+
},
|
| 676 |
+
"250081": {
|
| 677 |
+
"content": "▁<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": false
|
| 683 |
+
},
|
| 684 |
+
"250082": {
|
| 685 |
+
"content": "▁<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": false
|
| 691 |
+
},
|
| 692 |
+
"250083": {
|
| 693 |
+
"content": "▁<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": false
|
| 699 |
+
},
|
| 700 |
+
"250084": {
|
| 701 |
+
"content": "▁<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": false
|
| 707 |
+
},
|
| 708 |
+
"250085": {
|
| 709 |
+
"content": "▁<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": false
|
| 715 |
+
},
|
| 716 |
+
"250086": {
|
| 717 |
+
"content": "▁<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": false
|
| 723 |
+
},
|
| 724 |
+
"250087": {
|
| 725 |
+
"content": "▁<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": false
|
| 731 |
+
},
|
| 732 |
+
"250088": {
|
| 733 |
+
"content": "▁<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": false
|
| 739 |
+
},
|
| 740 |
+
"250089": {
|
| 741 |
+
"content": "▁<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": false
|
| 747 |
+
},
|
| 748 |
+
"250090": {
|
| 749 |
+
"content": "▁<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": false
|
| 755 |
+
},
|
| 756 |
+
"250091": {
|
| 757 |
+
"content": "▁<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": false
|
| 763 |
+
},
|
| 764 |
+
"250092": {
|
| 765 |
+
"content": "▁<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": false
|
| 771 |
+
},
|
| 772 |
+
"250093": {
|
| 773 |
+
"content": "▁<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": false
|
| 779 |
+
},
|
| 780 |
+
"250094": {
|
| 781 |
+
"content": "▁<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": false
|
| 787 |
+
},
|
| 788 |
+
"250095": {
|
| 789 |
+
"content": "▁<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": false
|
| 795 |
+
},
|
| 796 |
+
"250096": {
|
| 797 |
+
"content": "▁<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": false
|
| 803 |
+
},
|
| 804 |
+
"250097": {
|
| 805 |
+
"content": "▁<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": false
|
| 811 |
+
},
|
| 812 |
+
"250098": {
|
| 813 |
+
"content": "▁<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": false
|
| 819 |
+
},
|
| 820 |
+
"250099": {
|
| 821 |
+
"content": "▁<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": false
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [],
|
| 830 |
+
"clean_up_tokenization_spaces": true,
|
| 831 |
+
"eos_token": "</s>",
|
| 832 |
+
"extra_ids": 0,
|
| 833 |
+
"legacy": true,
|
| 834 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 835 |
+
"pad_token": "<pad>",
|
| 836 |
+
"sp_model_kwargs": {},
|
| 837 |
+
"tokenizer_class": "T5Tokenizer",
|
| 838 |
+
"unk_token": "<unk>"
|
| 839 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8202670216560364,
|
| 3 |
+
"best_model_checkpoint": "not_included_mt5-base/checkpoint-5000",
|
| 4 |
+
"epoch": 5.9880239520958085,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11976047904191617,
|
| 13 |
+
"grad_norm": 91.10150146484375,
|
| 14 |
+
"learning_rate": 0.0001976047904191617,
|
| 15 |
+
"loss": 10.8476,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.23952095808383234,
|
| 20 |
+
"grad_norm": 3.626096248626709,
|
| 21 |
+
"learning_rate": 0.00019520958083832338,
|
| 22 |
+
"loss": 1.901,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3592814371257485,
|
| 27 |
+
"grad_norm": 1.472233772277832,
|
| 28 |
+
"learning_rate": 0.00019281437125748504,
|
| 29 |
+
"loss": 1.5652,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.47904191616766467,
|
| 34 |
+
"grad_norm": 1.3357157707214355,
|
| 35 |
+
"learning_rate": 0.0001904191616766467,
|
| 36 |
+
"loss": 1.3415,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5988023952095808,
|
| 41 |
+
"grad_norm": 0.947651207447052,
|
| 42 |
+
"learning_rate": 0.0001880239520958084,
|
| 43 |
+
"loss": 1.233,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5988023952095808,
|
| 48 |
+
"eval_Accuracy": 0.062,
|
| 49 |
+
"eval_loss": 1.1174869537353516,
|
| 50 |
+
"eval_runtime": 22.1894,
|
| 51 |
+
"eval_samples_per_second": 225.333,
|
| 52 |
+
"eval_steps_per_second": 7.075,
|
| 53 |
+
"step": 500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.718562874251497,
|
| 57 |
+
"grad_norm": 0.8490985035896301,
|
| 58 |
+
"learning_rate": 0.00018562874251497007,
|
| 59 |
+
"loss": 1.1601,
|
| 60 |
+
"step": 600
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.8383233532934131,
|
| 64 |
+
"grad_norm": 0.8438432812690735,
|
| 65 |
+
"learning_rate": 0.00018323353293413173,
|
| 66 |
+
"loss": 1.1129,
|
| 67 |
+
"step": 700
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.9580838323353293,
|
| 71 |
+
"grad_norm": 0.7390198707580566,
|
| 72 |
+
"learning_rate": 0.00018083832335329342,
|
| 73 |
+
"loss": 1.0631,
|
| 74 |
+
"step": 800
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0778443113772456,
|
| 78 |
+
"grad_norm": 0.8146846890449524,
|
| 79 |
+
"learning_rate": 0.0001784431137724551,
|
| 80 |
+
"loss": 1.0243,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1976047904191618,
|
| 85 |
+
"grad_norm": 0.7685344815254211,
|
| 86 |
+
"learning_rate": 0.0001760479041916168,
|
| 87 |
+
"loss": 0.9898,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.1976047904191618,
|
| 92 |
+
"eval_Accuracy": 0.0998,
|
| 93 |
+
"eval_loss": 0.9793121814727783,
|
| 94 |
+
"eval_runtime": 22.9009,
|
| 95 |
+
"eval_samples_per_second": 218.332,
|
| 96 |
+
"eval_steps_per_second": 6.856,
|
| 97 |
+
"step": 1000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.3173652694610778,
|
| 101 |
+
"grad_norm": 0.7814993262290955,
|
| 102 |
+
"learning_rate": 0.00017365269461077845,
|
| 103 |
+
"loss": 0.9735,
|
| 104 |
+
"step": 1100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.437125748502994,
|
| 108 |
+
"grad_norm": 0.7339932322502136,
|
| 109 |
+
"learning_rate": 0.0001712574850299401,
|
| 110 |
+
"loss": 0.9723,
|
| 111 |
+
"step": 1200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.55688622754491,
|
| 115 |
+
"grad_norm": 0.7049471735954285,
|
| 116 |
+
"learning_rate": 0.0001688622754491018,
|
| 117 |
+
"loss": 0.9567,
|
| 118 |
+
"step": 1300
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.6766467065868262,
|
| 122 |
+
"grad_norm": 0.7287872433662415,
|
| 123 |
+
"learning_rate": 0.00016646706586826348,
|
| 124 |
+
"loss": 0.946,
|
| 125 |
+
"step": 1400
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.7964071856287425,
|
| 129 |
+
"grad_norm": 0.6998888254165649,
|
| 130 |
+
"learning_rate": 0.00016407185628742517,
|
| 131 |
+
"loss": 0.9204,
|
| 132 |
+
"step": 1500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.7964071856287425,
|
| 136 |
+
"eval_Accuracy": 0.1246,
|
| 137 |
+
"eval_loss": 0.9095961451530457,
|
| 138 |
+
"eval_runtime": 23.1954,
|
| 139 |
+
"eval_samples_per_second": 215.56,
|
| 140 |
+
"eval_steps_per_second": 6.769,
|
| 141 |
+
"step": 1500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.9161676646706587,
|
| 145 |
+
"grad_norm": 0.9079245328903198,
|
| 146 |
+
"learning_rate": 0.00016167664670658683,
|
| 147 |
+
"loss": 0.9237,
|
| 148 |
+
"step": 1600
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.035928143712575,
|
| 152 |
+
"grad_norm": 0.6102410554885864,
|
| 153 |
+
"learning_rate": 0.0001592814371257485,
|
| 154 |
+
"loss": 0.9064,
|
| 155 |
+
"step": 1700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.155688622754491,
|
| 159 |
+
"grad_norm": 0.6484932899475098,
|
| 160 |
+
"learning_rate": 0.00015688622754491018,
|
| 161 |
+
"loss": 0.8548,
|
| 162 |
+
"step": 1800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.2754491017964074,
|
| 166 |
+
"grad_norm": 0.6946207880973816,
|
| 167 |
+
"learning_rate": 0.00015449101796407186,
|
| 168 |
+
"loss": 0.8632,
|
| 169 |
+
"step": 1900
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.3952095808383236,
|
| 173 |
+
"grad_norm": 0.706642210483551,
|
| 174 |
+
"learning_rate": 0.00015209580838323355,
|
| 175 |
+
"loss": 0.8405,
|
| 176 |
+
"step": 2000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.3952095808383236,
|
| 180 |
+
"eval_Accuracy": 0.1388,
|
| 181 |
+
"eval_loss": 0.8839116096496582,
|
| 182 |
+
"eval_runtime": 22.9368,
|
| 183 |
+
"eval_samples_per_second": 217.99,
|
| 184 |
+
"eval_steps_per_second": 6.845,
|
| 185 |
+
"step": 2000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.5149700598802394,
|
| 189 |
+
"grad_norm": 0.7250691056251526,
|
| 190 |
+
"learning_rate": 0.0001497005988023952,
|
| 191 |
+
"loss": 0.8546,
|
| 192 |
+
"step": 2100
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.6347305389221556,
|
| 196 |
+
"grad_norm": 0.7567930817604065,
|
| 197 |
+
"learning_rate": 0.0001473053892215569,
|
| 198 |
+
"loss": 0.8508,
|
| 199 |
+
"step": 2200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.754491017964072,
|
| 203 |
+
"grad_norm": 0.8484090566635132,
|
| 204 |
+
"learning_rate": 0.00014491017964071858,
|
| 205 |
+
"loss": 0.851,
|
| 206 |
+
"step": 2300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.874251497005988,
|
| 210 |
+
"grad_norm": 0.8208755254745483,
|
| 211 |
+
"learning_rate": 0.00014251497005988024,
|
| 212 |
+
"loss": 0.843,
|
| 213 |
+
"step": 2400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.9940119760479043,
|
| 217 |
+
"grad_norm": 0.6463755965232849,
|
| 218 |
+
"learning_rate": 0.00014011976047904193,
|
| 219 |
+
"loss": 0.8338,
|
| 220 |
+
"step": 2500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.9940119760479043,
|
| 224 |
+
"eval_Accuracy": 0.1382,
|
| 225 |
+
"eval_loss": 0.852607786655426,
|
| 226 |
+
"eval_runtime": 23.4307,
|
| 227 |
+
"eval_samples_per_second": 213.396,
|
| 228 |
+
"eval_steps_per_second": 6.701,
|
| 229 |
+
"step": 2500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.1137724550898205,
|
| 233 |
+
"grad_norm": 0.708572506904602,
|
| 234 |
+
"learning_rate": 0.00013772455089820359,
|
| 235 |
+
"loss": 0.7838,
|
| 236 |
+
"step": 2600
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.2335329341317367,
|
| 240 |
+
"grad_norm": 0.758407711982727,
|
| 241 |
+
"learning_rate": 0.00013532934131736527,
|
| 242 |
+
"loss": 0.7792,
|
| 243 |
+
"step": 2700
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.3532934131736525,
|
| 247 |
+
"grad_norm": 0.8018171191215515,
|
| 248 |
+
"learning_rate": 0.00013293413173652696,
|
| 249 |
+
"loss": 0.7873,
|
| 250 |
+
"step": 2800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.4730538922155687,
|
| 254 |
+
"grad_norm": 0.6300553679466248,
|
| 255 |
+
"learning_rate": 0.00013053892215568865,
|
| 256 |
+
"loss": 0.774,
|
| 257 |
+
"step": 2900
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.592814371257485,
|
| 261 |
+
"grad_norm": 0.5713552832603455,
|
| 262 |
+
"learning_rate": 0.0001281437125748503,
|
| 263 |
+
"loss": 0.783,
|
| 264 |
+
"step": 3000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.592814371257485,
|
| 268 |
+
"eval_Accuracy": 0.1508,
|
| 269 |
+
"eval_loss": 0.8408400416374207,
|
| 270 |
+
"eval_runtime": 23.0015,
|
| 271 |
+
"eval_samples_per_second": 217.377,
|
| 272 |
+
"eval_steps_per_second": 6.826,
|
| 273 |
+
"step": 3000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.712574850299401,
|
| 277 |
+
"grad_norm": 0.6296516060829163,
|
| 278 |
+
"learning_rate": 0.00012574850299401196,
|
| 279 |
+
"loss": 0.7694,
|
| 280 |
+
"step": 3100
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.8323353293413174,
|
| 284 |
+
"grad_norm": 0.5926547050476074,
|
| 285 |
+
"learning_rate": 0.00012335329341317365,
|
| 286 |
+
"loss": 0.7878,
|
| 287 |
+
"step": 3200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.9520958083832336,
|
| 291 |
+
"grad_norm": 0.8825701475143433,
|
| 292 |
+
"learning_rate": 0.00012095808383233534,
|
| 293 |
+
"loss": 0.7683,
|
| 294 |
+
"step": 3300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.07185628742515,
|
| 298 |
+
"grad_norm": 0.7714102268218994,
|
| 299 |
+
"learning_rate": 0.00011856287425149701,
|
| 300 |
+
"loss": 0.7411,
|
| 301 |
+
"step": 3400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 4.191616766467066,
|
| 305 |
+
"grad_norm": 0.7947181463241577,
|
| 306 |
+
"learning_rate": 0.0001161676646706587,
|
| 307 |
+
"loss": 0.7288,
|
| 308 |
+
"step": 3500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.191616766467066,
|
| 312 |
+
"eval_Accuracy": 0.1602,
|
| 313 |
+
"eval_loss": 0.8330999612808228,
|
| 314 |
+
"eval_runtime": 23.0702,
|
| 315 |
+
"eval_samples_per_second": 216.73,
|
| 316 |
+
"eval_steps_per_second": 6.805,
|
| 317 |
+
"step": 3500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.311377245508982,
|
| 321 |
+
"grad_norm": 0.7584651112556458,
|
| 322 |
+
"learning_rate": 0.00011377245508982037,
|
| 323 |
+
"loss": 0.7258,
|
| 324 |
+
"step": 3600
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.431137724550898,
|
| 328 |
+
"grad_norm": 0.6492884159088135,
|
| 329 |
+
"learning_rate": 0.00011137724550898203,
|
| 330 |
+
"loss": 0.7222,
|
| 331 |
+
"step": 3700
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.550898203592815,
|
| 335 |
+
"grad_norm": 0.7623780965805054,
|
| 336 |
+
"learning_rate": 0.00010898203592814371,
|
| 337 |
+
"loss": 0.7168,
|
| 338 |
+
"step": 3800
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.6706586826347305,
|
| 342 |
+
"grad_norm": 0.8104670643806458,
|
| 343 |
+
"learning_rate": 0.00010658682634730539,
|
| 344 |
+
"loss": 0.7272,
|
| 345 |
+
"step": 3900
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.790419161676647,
|
| 349 |
+
"grad_norm": 0.6871969699859619,
|
| 350 |
+
"learning_rate": 0.00010419161676646707,
|
| 351 |
+
"loss": 0.7204,
|
| 352 |
+
"step": 4000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.790419161676647,
|
| 356 |
+
"eval_Accuracy": 0.159,
|
| 357 |
+
"eval_loss": 0.8263267874717712,
|
| 358 |
+
"eval_runtime": 22.9773,
|
| 359 |
+
"eval_samples_per_second": 217.606,
|
| 360 |
+
"eval_steps_per_second": 6.833,
|
| 361 |
+
"step": 4000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.910179640718563,
|
| 365 |
+
"grad_norm": 0.7578293085098267,
|
| 366 |
+
"learning_rate": 0.00010179640718562875,
|
| 367 |
+
"loss": 0.727,
|
| 368 |
+
"step": 4100
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.029940119760479,
|
| 372 |
+
"grad_norm": 0.71566241979599,
|
| 373 |
+
"learning_rate": 9.940119760479042e-05,
|
| 374 |
+
"loss": 0.7111,
|
| 375 |
+
"step": 4200
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 5.149700598802395,
|
| 379 |
+
"grad_norm": 0.7744144201278687,
|
| 380 |
+
"learning_rate": 9.700598802395209e-05,
|
| 381 |
+
"loss": 0.6699,
|
| 382 |
+
"step": 4300
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 5.269461077844311,
|
| 386 |
+
"grad_norm": 0.7886649370193481,
|
| 387 |
+
"learning_rate": 9.461077844311378e-05,
|
| 388 |
+
"loss": 0.6791,
|
| 389 |
+
"step": 4400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.389221556886228,
|
| 393 |
+
"grad_norm": 0.7046491503715515,
|
| 394 |
+
"learning_rate": 9.221556886227547e-05,
|
| 395 |
+
"loss": 0.6533,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.389221556886228,
|
| 400 |
+
"eval_Accuracy": 0.1644,
|
| 401 |
+
"eval_loss": 0.8296283483505249,
|
| 402 |
+
"eval_runtime": 23.2437,
|
| 403 |
+
"eval_samples_per_second": 215.112,
|
| 404 |
+
"eval_steps_per_second": 6.755,
|
| 405 |
+
"step": 4500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.508982035928144,
|
| 409 |
+
"grad_norm": 0.6836217641830444,
|
| 410 |
+
"learning_rate": 8.982035928143712e-05,
|
| 411 |
+
"loss": 0.6798,
|
| 412 |
+
"step": 4600
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.62874251497006,
|
| 416 |
+
"grad_norm": 0.8316423296928406,
|
| 417 |
+
"learning_rate": 8.742514970059881e-05,
|
| 418 |
+
"loss": 0.6813,
|
| 419 |
+
"step": 4700
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.748502994011976,
|
| 423 |
+
"grad_norm": 0.806846022605896,
|
| 424 |
+
"learning_rate": 8.502994011976048e-05,
|
| 425 |
+
"loss": 0.6797,
|
| 426 |
+
"step": 4800
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.868263473053892,
|
| 430 |
+
"grad_norm": 0.7254876494407654,
|
| 431 |
+
"learning_rate": 8.263473053892216e-05,
|
| 432 |
+
"loss": 0.6732,
|
| 433 |
+
"step": 4900
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.9880239520958085,
|
| 437 |
+
"grad_norm": 1.0394260883331299,
|
| 438 |
+
"learning_rate": 8.023952095808383e-05,
|
| 439 |
+
"loss": 0.6955,
|
| 440 |
+
"step": 5000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.9880239520958085,
|
| 444 |
+
"eval_Accuracy": 0.1616,
|
| 445 |
+
"eval_loss": 0.8202670216560364,
|
| 446 |
+
"eval_runtime": 23.0559,
|
| 447 |
+
"eval_samples_per_second": 216.864,
|
| 448 |
+
"eval_steps_per_second": 6.81,
|
| 449 |
+
"step": 5000
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"logging_steps": 100,
|
| 453 |
+
"max_steps": 8350,
|
| 454 |
+
"num_input_tokens_seen": 0,
|
| 455 |
+
"num_train_epochs": 10,
|
| 456 |
+
"save_steps": 500,
|
| 457 |
+
"stateful_callbacks": {
|
| 458 |
+
"EarlyStoppingCallback": {
|
| 459 |
+
"args": {
|
| 460 |
+
"early_stopping_patience": 5,
|
| 461 |
+
"early_stopping_threshold": 0.01
|
| 462 |
+
},
|
| 463 |
+
"attributes": {
|
| 464 |
+
"early_stopping_patience_counter": 0
|
| 465 |
+
}
|
| 466 |
+
},
|
| 467 |
+
"TrainerControl": {
|
| 468 |
+
"args": {
|
| 469 |
+
"should_epoch_stop": false,
|
| 470 |
+
"should_evaluate": false,
|
| 471 |
+
"should_log": false,
|
| 472 |
+
"should_save": true,
|
| 473 |
+
"should_training_stop": false
|
| 474 |
+
},
|
| 475 |
+
"attributes": {}
|
| 476 |
+
}
|
| 477 |
+
},
|
| 478 |
+
"total_flos": 4755250684394496.0,
|
| 479 |
+
"train_batch_size": 32,
|
| 480 |
+
"trial_name": null,
|
| 481 |
+
"trial_params": null
|
| 482 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39ded29f7a9e06ee17787eccb1bb18c65be308325a5187a24f9fae39c7fde641
|
| 3 |
+
size 5240
|